Daily Papers

Comprehensive, unbiased, and comparable evaluation of modern generalist policies is uniquely challenging: existing approaches for robot benchmarking typically rely on heavy standardization, either by specifying fixed evaluation tasks and environments, or by hosting centralized ''robot challenges'', and do not readily scale to evaluating generalist policies across a broad range of tasks and environments. In this work, we propose RoboArena, a new approach for scalable evaluation of generalist robot policies in the real world. Instead of standardizing evaluations around fixed tasks, environments, or locations, we propose to crowd-source evaluations across a distributed network of evaluators. Importantly, evaluators can freely choose the tasks and environments they evaluate on, enabling easy scaling of diversity, but they are required to perform double-blind evaluations over pairs of policies. Then, by aggregating preference feedback from pairwise comparisons across diverse tasks and environments, we can derive a ranking of policies. We instantiate our approach across a network of evaluators at seven academic institutions using the DROID robot platform. Through more than 600 pairwise real-robot evaluation episodes across seven generalist policies, we demonstrate that our crowd-sourced approach can more accurately rank the performance of existing generalist policies than conventional, centralized evaluation approaches, while being more scalable, resilient, and trustworthy. We open our evaluation network to the community and hope that it can enable more accessible comparisons of generalist robot policies.

Autonomous systems that generate scientific hypotheses, conduct experiments, and draft manuscripts have recently emerged as a promising paradigm for accelerating discovery. However, existing AI Scientists remain largely domain-agnostic, limiting their applicability to clinical medicine, where research is required to be grounded in medical evidence with specialized data modalities. In this work, we introduce Medical AI Scientist, the first autonomous research framework tailored to clinical autonomous research. It enables clinically grounded ideation by transforming extensively surveyed literature into actionable evidence through clinician-engineer co-reasoning mechanism, which improves the traceability of generated research ideas. It further facilitates evidence-grounded manuscript drafting guided by structured medical compositional conventions and ethical policies. The framework operates under 3 research modes, namely paper-based reproduction, literature-inspired innovation, and task-driven exploration, each corresponding to a distinct level of automated scientific inquiry with progressively increasing autonomy. Comprehensive evaluations by both large language models and human experts demonstrate that the ideas generated by the Medical AI Scientist are of substantially higher quality than those produced by commercial LLMs across 171 cases, 19 clinical tasks, and 6 data modalities. Meanwhile, our system achieves strong alignment between the proposed method and its implementation, while also demonstrating significantly higher success rates in executable experiments. Double-blind evaluations by human experts and the Stanford Agentic Reviewer suggest that the generated manuscripts approach MICCAI-level quality, while consistently surpassing those from ISBI and BIBM. The proposed Medical AI Scientist highlights the potential of leveraging AI for autonomous scientific discovery in healthcare.

This study presents PARROT (Persuasion and Agreement Robustness Rating of Output Truth), a robustness focused framework designed to measure the degradation in accuracy that occurs under social pressure exerted on users through authority and persuasion in large language models (LLMs) the phenomenon of sycophancy (excessive conformity). PARROT (i) isolates causal effects by comparing the neutral version of the same question with an authoritatively false version using a double-blind evaluation, (ii) quantifies confidence shifts toward the correct and imposed false responses using log-likelihood-based calibration tracking, and (iii) systematically classifies failure modes (e.g., robust correct, sycophantic agreement, reinforced error, stubborn error, self-correction, etc.) using an eight-state behavioral taxonomy. We evaluated 22 models using 1,302 MMLU-style multiple-choice questions across 13 domains and domain-specific authority templates. Findings show marked heterogeneity: advanced models (e.g., GPT-5, GPT-4.1, Claude Sonnet 4.5) exhibit low "follow rates" (leq 11%, GPT-5: 4\%) and minimal accuracy loss, while older/smaller models show severe epistemic collapse (GPT-4: 80\%, Qwen 2.5-1.5B: 94\%). The danger is not limited to response changes; weak models reduce confidence in the correct response while increasing confidence in the imposed incorrect response. While international law and global knowledge at the domain level exhibit high fragility, elementary mathematics is relatively resilient. Consequently, we argue that the goal of "resistance to overfitting pressure" should be addressed as a primary objective alongside accuracy, harm avoidance, and privacy for safe deployment in the real world.

Structure-property relationships are foundational to biology, chemistry and materials science, where function, reactivity and physical response emerge from spatial, chemical and periodic organization. Mechanistically explaining these relationships requires interpreting structural evidence through scientific principles and physical constraints, from stereochemistry and bonding to symmetry, energetics and periodic order. However, applying artificial intelligence to this process presents a joint challenge of representation and reasoning: models must preserve domain-native structural information while showing how specific evidence supports predictions under these constraints. Here we introduce SciReasoner, a multimodal scientific foundation model for native structural reasoning across proteins, small molecules and inorganic crystals. SciReasoner discretizes coordinates, topologies and periodic connectivities into a unified structure-aware vocabulary, treating structural tokens as addressable evidence units during reasoning. In homology-controlled Gene Ontology prediction, SciReasoner improves Cellular Component annotation for low-homology and orphan-like proteins, increasing F_{max} from 0.42 to 0.55. In chemistry, it raises single-step retrosynthesis accuracy from 0.63 to 0.72 while generating fragment-level disconnection and precursor-verification traces. In materials science, its representations separate elemental and compound phases and resolve high- and low-band-gap regimes. Across 86 benchmarks, SciReasoner achieves state-of-the-art performance on 67 tasks. Double-blind expert evaluation rates its reasoning traces as preferred or at least comparable to those of a frontier large language model in 98% of cases. By making structure an inspectable substrate for reasoning under scientific constraints, SciReasoner connects accurate prediction with interpretable scientific inference.

We introduce Matrix-Game, an interactive world foundation model for controllable game world generation. Matrix-Game is trained using a two-stage pipeline that first performs large-scale unlabeled pretraining for environment understanding, followed by action-labeled training for interactive video generation. To support this, we curate Matrix-Game-MC, a comprehensive Minecraft dataset comprising over 2,700 hours of unlabeled gameplay video clips and over 1,000 hours of high-quality labeled clips with fine-grained keyboard and mouse action annotations. Our model adopts a controllable image-to-world generation paradigm, conditioned on a reference image, motion context, and user actions. With over 17 billion parameters, Matrix-Game enables precise control over character actions and camera movements, while maintaining high visual quality and temporal coherence. To evaluate performance, we develop GameWorld Score, a unified benchmark measuring visual quality, temporal quality, action controllability, and physical rule understanding for Minecraft world generation. Extensive experiments show that Matrix-Game consistently outperforms prior open-source Minecraft world models (including Oasis and MineWorld) across all metrics, with particularly strong gains in controllability and physical consistency. Double-blind human evaluations further confirm the superiority of Matrix-Game, highlighting its ability to generate perceptually realistic and precisely controllable videos across diverse game scenarios. To facilitate future research on interactive image-to-world generation, we will open-source the Matrix-Game model weights and the GameWorld Score benchmark at https://github.com/SkyworkAI/Matrix-Game.

Advances in AI-assisted research have introduced powerful tools for literature retrieval, hypothesis generation, experimentation, and manuscript preparation. However, systems remain fragmented and lack human-centred workflows. To address these gaps, we introduce AIssistant, an agentic, open-source Human-AI collaborative framework designed to simplify the end-to-end creation of scientific workflows. Since our development is still in an early stage, we present here the first experiments with AIssistant for perspective and review research papers in machine learning. Our system integrates modular tools and agents for literature synthesis, section-wise experimentation, citation management, and automatic LaTeX paper text generation, while maintaining human oversight at every stage to ensure accuracy, coherence, and scholarly rigour. We conducted a comprehensive evaluation across three layers: (1) Independent Human Review, following NeurIPS double-blind standards; (2) Automated LLM Review, using GPT-5 as a scalable human review proxy; and (3) Program Chair Oversight, where the chair monitors the entire review process and makes final validation and acceptance decisions. The results demonstrate that AIssistant improves drafting efficiency and thematic consistency. Nonetheless, Human-AI collaboration remains essential for maintaining factual correctness, methodological soundness, and ethical compliance. Despite its effectiveness, we identify key limitations, including hallucinated citations, difficulty adapting to dynamic paper structures, and incomplete integration of multimodal content.

Animation has gained significant interest in the recent film and TV industry. Despite the success of advanced video generation models like Sora, Kling, and CogVideoX in generating natural videos, they lack the same effectiveness in handling animation videos. Evaluating animation video generation is also a great challenge due to its unique artist styles, violating the laws of physics and exaggerated motions. In this paper, we present a comprehensive system, AniSora, designed for animation video generation, which includes a data processing pipeline, a controllable generation model, and an evaluation dataset. Supported by the data processing pipeline with over 10M high-quality data, the generation model incorporates a spatiotemporal mask module to facilitate key animation production functions such as image-to-video generation, frame interpolation, and localized image-guided animation. We also collect an evaluation benchmark of 948 various animation videos, the evaluation on VBench and human double-blind test demonstrates consistency in character and motion, achieving state-of-the-art results in animation video generation. Our evaluation benchmark will be publicly available at https://github.com/bilibili/Index-anisora.

This paper introduces a novel double stimulus subjective assessment methodology for the evaluation of high quality images to address the limitations of existing protocols in detecting subtle perceptual differences. The In-place Double Stimulus Quality Scale (IDSQS) allows subjects to alternately view a reference and a distorted image at the same spatial location, facilitating a more intuitive detection of differences in quality, especially at high to visually lossless quality levels. A large-scale crowdsourcing study employing this methodology was conducted, generating a comprehensive public dataset to evaluate perceived image quality across several compression algorithms and distortion levels. An additional contribution is the modeling of quality scores using a Beta distribution, allowing for the assessment of variability and subject consistency. Our findings demonstrate the effectiveness of the IDSQS methodology in achieving high correlation with more precise subjective evaluation benchmarks. The dataset, subjective data, and graphical user interface developed for this study are publicly available at https://github.com/shimamohammadi/IDSQS

Empirical evaluation serves as the primary compass guiding research progress in foundation models. Despite a large body of work focused on training frontier vision-language models (VLMs), approaches to their evaluation remain nascent. To guide their maturation, we propose three desiderata that evaluations should satisfy: (1) faithfulness to the modality and application, (2) discriminability between models of varying quality, and (3) efficiency in compute. Through this lens, we identify critical failure modes that violate faithfulness and discriminability, misrepresenting model capabilities: (i) multiple-choice formats reward guessing, poorly reflect downstream use cases, and saturate early as models improve; (ii) blindly solvable questions, which can be answered without images, constitute up to 70% of some evaluations; and (iii) mislabeled or ambiguous samples compromise up to 42% of examples in certain datasets. Regarding efficiency, the computational burden of evaluating frontier models has become prohibitive: by some accounts, nearly 20% of development compute is devoted to evaluation alone. Rather than discarding existing benchmarks, we curate them via transformation and filtering to maximize fidelity and discriminability. We find that converting multiple-choice questions to generative tasks reveals sharp capability drops of up to 35%. In addition, filtering blindly solvable and mislabeled samples improves discriminative power while simultaneously reducing computational cost. We release DatBench-Full, a cleaned evaluation suite of 33 datasets spanning nine VLM capabilities, and DatBench, a discriminative subset that achieves 13x average speedup (up to 50x) while closely matching the discriminative power of the original datasets. Our work outlines a path toward evaluation practices that are both rigorous and sustainable as VLMs continue to scale.

ARC Challenge appears more difficult than ARC Easy for modern LLMs primarily due to an evaluation setup that prevents direct comparison of answer choices rather than inherent complexity. Although some researchers have quietly shifted to a more appropriate scheme over the last year, the implications of this change have yet to be widely acknowledged. We highlight this overlooked shift, show how similar evaluation practices falsely imply reasoning deficits in other benchmarks, and demonstrate that fairer methods dramatically reduce performance gaps (e.g. on SIQA) and even yield superhuman results (OpenBookQA). In doing so, we reveal how evaluation shapes perceived difficulty and offer guidelines to ensure that multiple-choice evaluations accurately reflect actual model capabilities.

Large Vision-Language Models (VLMs) are increasingly used to evaluate outputs of other models, for image-to-text (I2T) tasks such as visual question answering, and text-to-image (T2I) generation tasks. Despite this growing reliance, the reliability of these Evaluator VLMs remains under explored. In this work, we systematically evaluate the reliability of Evaluator VLMs across both I2T and T2I tasks. We introduce targeted perturbations that degrade output quality along key error dimensions, including object hallucinations, spatial reasoning, factual grounding, and visual fidelity. These perturbations test whether Evaluator VLMs can reliably account for these quality degrading errors in their evaluations. Using a comprehensive benchmark of over 4000 perturbed instances spanning 40 perturbation dimensions, we evaluate 4 prominent VLMs using single-answer scoring, pairwise comparison, and reference-guided paradigms. Our findings reveal that current VLM evaluators exhibit substantial blind spots: they often fail to detect perturbed outputs - in some cases exceeding 50%, struggle particularly with fine-grained compositional and spatial errors, and are often insensitive to hallucinated content that contradicts the input image. Pairwise comparison proves more reliable, though failure rates persist. These results highlight the unreliable nature of current Evaluator VLMs and urge caution in their deployment for benchmarking and development decisions. Code and data have been made publicly available.

Modern AI models achieve strong performance on many established benchmarks, yet they still fail on tasks that humans find almost trivial, such as manipulating a string or drawing a dog with five legs. These examples suggest that existing benchmarks may under-measure persistent blind spots in current systems. We introduce blind-spots-bench, a benchmark designed to expose such blind spots through tasks that appear simple for humans but remain challenging for modern AI. We collect raw questions from students in an AI course, clean and annotate them with structured reference solutions, and propose a task taxonomy tailored to the resulting dataset of 235 samples. We further develop an automated grading pipeline to evaluate a wide range of models, including open-weight and closed-source language, vision-language, and image-generation models. Our analysis on blind-spots-bench reveals that closed-source frontier models can substantially outperform open-weight models with even approx10% gap, even when they attain comparable performance on existing benchmarks. A more fine-grained analysis shows that no single model dominates across all task types, and that some tasks remain challenging for all evaluated models. These results highlight the value of blind-spots-bench as a diagnostic stress test for identifying concrete weaknesses in current modern models.

Instruction-tuned large language models produce helpful, structured responses, but how robust is this helpfulness under trivial constraints? We show that simple lexical constraints (banning a single punctuation character or common word) cause instruction-tuned LLMs to collapse their responses, losing 14--48\% of comprehensiveness across seven models spanning five families (7B--70B, open- and closed-weight). A blinded human evaluation with 10 STEM-trained evaluators confirms genuine content loss, with information criteria degrading 1.5--2.3times more than surface criteria, a finding corroborated by over 4,100 automated pairwise comparisons (77--100\% baseline preference) across three LLM judges from two model families. Diagnostic analysis identifies this as a planning failure: two-pass generation recovers 59--96\% of response length, and linear probes on prompt representations predict response length with R^2 = 0.51--0.94 before generation begins. The same probes yield negative R^2 on base models, confirming that instruction tuning introduces the representational structure underlying the collapse. Base models show no systematic degradation under identical constraints, demonstrating that instruction tuning couples task competence to narrow surface-form templates. The effect extends to realistic deployment constraints (preamble suppression, corporate tone guidelines, legal compliance hedging, accessibility requirements) causing comparable degradation (-22\% to -34\%), with suppressing the conversational opener alone (``Certainly!'') causing 40\% collapse on our most fragile model despite restricting only the opening tokens. We further show that standard independent LLM-as-judge evaluation detects only a 3.5\% quality drop where pairwise evaluation reveals 23\%, exposing a methodological blind spot in current evaluation practice.

Recently, there has been a trend of evaluating the Large Language Model (LLM) quality in the flavor of LLM-as-a-Judge, namely leveraging another LLM to evaluate the current output quality. However, existing judges are proven to be biased, namely they would favor answers which present better superficial quality (such as verbosity, fluency) while ignoring the instruction following ability. In this work, we propose systematic research about the bias of LLM-as-a-Judge. Specifically, for closed-source judge models, we apply calibration to mitigate the significance of superficial quality, both on probability level and prompt level. For open-source judge models, we propose to mitigate the bias by contrastive training, with curated negative samples that deviate from instruction but present better superficial quality. We apply our methods on the bias evaluation benchmark, and experiment results show our methods mitigate the bias by a large margin while maintaining a satisfactory evaluation accuracy.

Closed-loop decision-making systems (e.g., lending, screening, or recidivism risk assessment) often operate under fairness and service constraints while inducing feedback effects: decisions change who appears in the future, yielding non-stationary data and potentially amplifying disparities. We study online learning of a one-dimensional threshold policy from bandit feedback under demographic parity (DP) and, optionally, service-rate constraints. The learner observes only a scalar score each round and selects a threshold; reward and constraint residuals are revealed only for the chosen threshold. We propose Optimistic Feasible Search (OFS), a simple grid-based method that maintains confidence bounds for reward and constraint residuals for each candidate threshold. At each round, OFS selects a threshold that appears feasible under confidence bounds and, among those, maximizes optimistic reward; if no threshold appears feasible, OFS selects the threshold minimizing optimistic constraint violation. This design directly targets feasible high-utility thresholds and is particularly effective for low-dimensional, interpretable policy classes where discretization is natural. We evaluate OFS on (i) a synthetic closed-loop benchmark with stable contraction dynamics and (ii) two semi-synthetic closed-loop benchmarks grounded in German Credit and COMPAS, constructed by training a score model and feeding group-dependent acceptance decisions back into population composition. Across all environments, OFS achieves higher reward with smaller cumulative constraint violation than unconstrained and primal-dual bandit baselines, and is near-oracle relative to the best feasible fixed threshold under the same sweep procedure. Experiments are reproducible and organized with double-blind-friendly relative outputs.

Blind image quality assessment (BIQA) is commonly built on two basic learning paradigms: regression and ranking. Regression calibrates absolute scores, whereas ranking recovers quality structure from ordinal relations. Although joint regression-ranking supervision often improves BIQA, the relation between the two paradigms remains largely empirical and underexplored. In this work, we revisit what underlies regression and ranking and identify pairwise relational distance, termed quality margin, as their common bridge. Our derivation shows that, at the objective-optimization level, both paradigms fit quality margins: regression fits margins induced by score endpoints, while ranking fits transformed or sign-level margins through preference probabilities. Motivated by this insight, we propose MR-IQA, a direct quality-margin optimization framework for reinforcement learning (RL)-based BIQA. MR-IQA samples quality scores and optimizes pairwise margin errors as policy rewards, thereby modeling quality structure more explicitly. Experiments on six BIQA benchmarks show competitive general performance, and controlled comparisons demonstrate that MR-IQA achieves the strongest average PLCC/SRCC over regression- or ranking-based RL methods. Our findings provide a new insight into unifying regression and ranking, offering a theoretical basis for understanding quality-structure modeling in BIQA and beyond.

AI systems can fail silently. The failure propagates through training loops, evaluation pipelines, and production monitoring stacks until downstream harm makes it visible. This paper introduces evaluation blindness: a measurement function M exhibits evaluation blindness with respect to failure class F when it produces readings indistinguishable from a healthy state while the system is actually failing, with no auxiliary signal flagging the gap. The problem surfaces at two lifecycle stages the literature has treated separately. At training time, reward models are gamed, importance-sampling corrections are silently miscalculated, and benchmark contamination inflates fine-tuning evaluations, all while loss curves look healthy and gradient updates proceed normally. At deployment time, monitoring fails to catch six classes of production failure, including an Operational category that is 100% silent by structural definition. We provide a formal detectability predicate unifying both stages. Four training-time case studies trace concrete breakdowns, including a real implementation bug in TRL PR #6594 where gradients are corrupted as loss decreases normally. A six-class taxonomy validated against 50 real-world incidents from court documents and regulatory filings finds that 53% of verifiable public failures were silent. A failure budget framework ties acceptable failure rates to use-case risk class. The implication is direct: measurement infrastructure is a correctness concern across the full AI lifecycle, not just at evaluation time. Data, code, and taxonomy schema are at https://github.com/priyanka25aug/llm-failure-taxonomy.

Evaluation has traditionally focused on ranking candidates for a specific skill. Modern generalist models, such as Large Language Models (LLMs), decidedly outpace this paradigm. Open-ended evaluation systems, where candidate models are compared on user-submitted prompts, have emerged as a popular solution. Despite their many advantages, we show that the current Elo-based rating systems can be susceptible to and even reinforce biases in data, intentional or accidental, due to their sensitivity to redundancies. To address this issue, we propose evaluation as a 3-player game, and introduce novel game-theoretic solution concepts to ensure robustness to redundancy. We show that our method leads to intuitive ratings and provide insights into the competitive landscape of LLM development.

The ``LLM-as-a-judge'' paradigm has become a standard method for evaluating open-ended generation. To address the quadratic scalability costs of pairwise comparisons, popular benchmarks like Arena-Hard and AlpacaEval compare all models against a single anchor. However, despite its widespread use, the impact of anchor selection on the reliability of the results remains largely unexplored. In this work, we systematically investigate the effect of anchor selection by evaluating 22 different anchors on the Arena-Hard-v2.0 dataset. We find that the choice of anchor is critical: a poor anchor can dramatically reduce correlation with human rankings. We identify that common anchor choices (best-performing and worst-performing models) make poor anchors. Because these extreme anchors are consistently better or worse than all other models, they are seldom indicative of the relative ranking of the models. We further quantify the effect size of anchor selection, showing it is comparable to the selection of a judge model. We conclude with actionable recommendations. First, we conduct a power analysis, and compute sufficient benchmark sizes for anchor-based evaluation, finding that standard benchmark sizes are insufficient for pairwise evaluation and fail to distinguish between competitive models reliably. Second, we provide guidelines for selecting informative anchors to ensure reliable and efficient evaluation practices.

As language models shift from single-shot answer generation toward multi-step reasoning that retrieves and consumes evidence mid-inference, evaluating the role of individual retrieved items becomes more important. Existing RAG evaluation typically targets final-answer quality, citation faithfulness, or answer-level attribution, but none of these directly targets the intervention-based, per-evidence-item utility view we study here. We introduce CUE-R, a lightweight intervention-based framework for measuring per-evidence-item operational utility in single-shot RAG using shallow observable retrieval-use traces. CUE-R perturbs individual evidence items via REMOVE, REPLACE, and DUPLICATE operators, then measures changes along three utility axes (correctness, proxy-based grounding faithfulness, and confidence error) plus a trace-divergence signal. We also outline an operational evidence-role taxonomy for interpreting intervention outcomes. Experiments on HotpotQA and 2WikiMultihopQA with Qwen-3 8B and GPT-5.2 reveal a consistent pattern: REMOVE and REPLACE substantially harm correctness and grounding while producing large trace shifts, whereas DUPLICATE is often answer-redundant yet not fully behaviorally neutral. A zero-retrieval control confirms that these effects arise from degradation of meaningful retrieval. A two-support ablation further shows that multi-hop evidence items can interact non-additively: removing both supports harms performance far more than either single removal. Our results suggest that answer-only evaluation misses important evidence effects and that intervention-based utility analysis is a practical complement for RAG evaluation.

While dialogue remains an important end-goal of natural language research, the difficulty of evaluation is an oft-quoted reason why it remains troublesome to make real progress towards its solution. Evaluation difficulties are actually two-fold: not only do automatic metrics not correlate well with human judgments, but also human judgments themselves are in fact difficult to measure. The two most used human judgment tests, single-turn pairwise evaluation and multi-turn Likert scores, both have serious flaws as we discuss in this work. We instead provide a novel procedure involving comparing two full dialogues, where a human judge is asked to pay attention to only one speaker within each, and make a pairwise judgment. The questions themselves are optimized to maximize the robustness of judgments across different annotators, resulting in better tests. We also show how these tests work in self-play model chat setups, resulting in faster, cheaper tests. We hope these tests become the de facto standard, and will release open-source code to that end.

We present EgoBlind, the first egocentric VideoQA dataset collected from blind individuals to evaluate the assistive capabilities of contemporary multimodal large language models (MLLMs). EgoBlind comprises 1,392 first-person videos from the daily lives of blind and visually impaired individuals. It also features 5,311 questions directly posed or verified by the blind to reflect their in-situation needs for visual assistance. Each question has an average of 3 manually annotated reference answers to reduce subjectiveness. Using EgoBlind, we comprehensively evaluate 16 advanced MLLMs and find that all models struggle. The best performers achieve an accuracy near 60\%, which is far behind human performance of 87.4\%. To guide future advancements, we identify and summarize major limitations of existing MLLMs in egocentric visual assistance for the blind and explore heuristic solutions for improvement. With these efforts, we hope that EgoBlind will serve as a foundation for developing effective AI assistants to enhance the independence of the blind and visually impaired. Data and code are available at https://github.com/doc-doc/EgoBlind.

The recent emergence of Large Vision-Language Models(VLMs) has resulted in a variety of different benchmarks for evaluating such models. Despite this, we observe that most existing evaluation methods suffer from the fact that they either require the model to choose from pre-determined responses, sacrificing open-endedness, or evaluate responses using a judge model, resulting in subjective and unreliable evaluation. In addition, we observe a lack of benchmarks for VLMs in the Korean language, which are necessary as a separate metric from more common English language benchmarks, as the performance of generative language models can differ significantly based on the language being used. Therefore, we present KOFFVQA, a general-purpose free-form visual question answering benchmark in the Korean language for the evaluation of VLMs. Our benchmark consists of 275 carefully crafted questions each paired with an image and grading criteria covering 10 different aspects of VLM performance. The grading criteria eliminate the problem of unreliability by allowing the judge model to grade each response based on a pre-determined set of rules. By defining the evaluation criteria in an objective manner, even a small open-source model can be used to evaluate models on our benchmark reliably. In addition to evaluating a large number of existing VLMs on our benchmark, we also experimentally verify that our method of using pre-existing grading criteria for evaluation is much more reliable than existing methods. Our evaluation code is available at https://github.com/maum-ai/KOFFVQA

Human evaluation is critical for validating the performance of text-to-image generative models, as this highly cognitive process requires deep comprehension of text and images. However, our survey of 37 recent papers reveals that many works rely solely on automatic measures (e.g., FID) or perform poorly described human evaluations that are not reliable or repeatable. This paper proposes a standardized and well-defined human evaluation protocol to facilitate verifiable and reproducible human evaluation in future works. In our pilot data collection, we experimentally show that the current automatic measures are incompatible with human perception in evaluating the performance of the text-to-image generation results. Furthermore, we provide insights for designing human evaluation experiments reliably and conclusively. Finally, we make several resources publicly available to the community to facilitate easy and fast implementations.

Correctly evaluating defenses against adversarial examples has proven to be extremely difficult. Despite the significant amount of recent work attempting to design defenses that withstand adaptive attacks, few have succeeded; most papers that propose defenses are quickly shown to be incorrect. We believe a large contributing factor is the difficulty of performing security evaluations. In this paper, we discuss the methodological foundations, review commonly accepted best practices, and suggest new methods for evaluating defenses to adversarial examples. We hope that both researchers developing defenses as well as readers and reviewers who wish to understand the completeness of an evaluation consider our advice in order to avoid common pitfalls.

Large vision-language models suffer from visual ungroundedness: they can produce a fluent, confident, and even correct response driven entirely by language priors, with the image contributing nothing to the prediction. Existing confidence estimation methods cannot detect this, as they observe model behavior under normal inference with no mechanism to determine whether a prediction was shaped by the image or by text alone. We introduce BICR (Blind-Image Contrastive Ranking), a model-agnostic confidence estimation framework that makes this contrast explicit during training by extracting hidden states from a frozen LVLM twice: once with the real image-question pair, and once with the image blacked out while the question is held fixed. A lightweight probe is trained on the real-image hidden state and regularized by a ranking loss that penalizes higher confidence on the blacked-out view, teaching it to treat visual grounding as a signal of reliability at zero additional inference cost. Evaluated across five modern LVLMs and seven baselines on a benchmark covering visual question answering, object hallucination detection, medical imaging, and financial document understanding, BICR achieves the best cross-LVLM average on both calibration and discrimination simultaneously, with statistically significant discrimination gains robust to cluster-aware analysis at 4-18x fewer parameters than the strongest probing baseline.

Independence testing is a fundamental and classical statistical problem that has been extensively studied in the batch setting when one fixes the sample size before collecting data. However, practitioners often prefer procedures that adapt to the complexity of a problem at hand instead of setting sample size in advance. Ideally, such procedures should (a) allow stopping earlier on easy tasks (and later on harder tasks), hence making better use of available resources, and (b) continuously monitor the data and efficiently incorporate statistical evidence after collecting new data, while controlling the false alarm rate. It is well known that classical batch tests are not tailored for streaming data settings: valid inference after data peeking requires correcting for multiple testing but such corrections generally result in low power. Following the principle of testing by betting, we design sequential kernelized independence tests (SKITs) that overcome such shortcomings. We exemplify our broad framework using bets inspired by kernelized dependence measures, e.g, the Hilbert-Schmidt independence criterion. Our test is valid under non-i.i.d. time-varying settings, for which there exist no batch tests. We demonstrate the power of our approaches on both simulated and real data.

We conduct a systematic study of 18 widely used vision-language benchmarks and identify three major issues: 1) many items do not rely on visual cues and therefore fail to effectively measure multimodal understanding; 2) many items are already close to performance saturation for current LVLMs, which limits their discriminative power; 3) a small number of anomalous items affect the reliability of evaluation results. To this end, we propose MMGist, a curated benchmark that covers seven capability dimensions and contains 7,262 items. MMGist is constructed through a three-stage pipeline, which sequentially combines text-ablation filtering, cross-model saturation filtering, and anomaly detection filtering. We conduct extensive experiments on 27 leading LVLMs and compare MMGist with the raw pool of 23,250 items. The results show that MMGist preserves model rankings with high fidelity, with Spearman ρ= 0.98, while reducing evaluation items by 69\% and improving cross-model discrimination by 78\%. Further results indicate that Visual Logic remains a systematic weakness of current LVLMs, while knowledge-intensive dimensions such as Expert Knowledge dimensions remain important factors for distinguishing closed-source models from open-source models. These findings suggest that high-quality evaluation should prioritize visual dependency, discriminative power, and reliability, rather than simply pursuing benchmark scale.

Machine learning has demonstrated remarkable performance over finite datasets, yet whether the scores over the fixed benchmarks can sufficiently indicate the model's performance in the real world is still in discussion. In reality, an ideal robust model will probably behave similarly to the oracle (e.g., the human users), thus a good evaluation protocol is probably to evaluate the models' behaviors in comparison to the oracle. In this paper, we introduce a new robustness measurement that directly measures the image classification model's performance compared with a surrogate oracle (i.e., a foundation model). Besides, we design a simple method that can accomplish the evaluation beyond the scope of the benchmarks. Our method extends the image datasets with new samples that are sufficiently perturbed to be distinct from the ones in the original sets, but are still bounded within the same image-label structure the original test image represents, constrained by a foundation model pretrained with a large amount of samples. As a result, our new method will offer us a new way to evaluate the models' robustness performance, free of limitations of fixed benchmarks or constrained perturbations, although scoped by the power of the oracle. In addition to the evaluation results, we also leverage our generated data to understand the behaviors of the model and our new evaluation strategies.

LLM-as-Judge frameworks are increasingly popular for AI evaluation, yet research findings on the relationship between models' generation and judgment abilities remain inconsistent. We investigate this relationship through systematic dataset- and instance-level analyses across 11 models and 21 diverse tasks. Despite both capabilities relying on the same underlying knowledge, our analyses reveal they are only weakly correlated, primarily due to LLMs' sensitivity to the responses being judged. To address this, we propose a self-reference-guided evaluation strategy that leverages a model's own answers as references. This approach significantly strengthens the correlation between generation and judgment abilities, offering a practical path to align these skills and providing a reliable proxy for model selection in evaluation tasks.

Evaluation efforts such as TREC, CLEF, NTCIR and FIRE, alongside public leaderboard such as MS MARCO, are intended to encourage research and track our progress, addressing big questions in our field. However, the goal is not simply to identify which run is "best", achieving the top score. The goal is to move the field forward by developing new robust techniques, that work in many different settings, and are adopted in research and practice. This paper uses the MS MARCO and TREC Deep Learning Track as our case study, comparing it to the case of TREC ad hoc ranking in the 1990s. We show how the design of the evaluation effort can encourage or discourage certain outcomes, and raising questions about internal and external validity of results. We provide some analysis of certain pitfalls, and a statement of best practices for avoiding such pitfalls. We summarize the progress of the effort so far, and describe our desired end state of "robust usefulness", along with steps that might be required to get us there.

Multiple choice benchmarks have long been the workhorse of language model evaluation because grading multiple choice is objective and easy to automate. However, we show multiple choice questions from popular benchmarks can often be answered without even seeing the question. These shortcuts arise from a fundamental limitation of discriminative evaluation not shared by evaluations of the model's free-form, generative answers. Until recently, there appeared to be no viable, scalable alternative to multiple choice--but, we show that this has changed. We consider generative evaluation via what we call answer matching: Give the candidate model the question without the options, have it generate a free-form response, then use a modern language model with the reference answer to determine if the response matches the reference. To compare the validity of different evaluation strategies, we annotate MMLU-Pro and GPQA-Diamond to obtain human grading data, and measure the agreement of each evaluation approach. We find answer matching using recent models--even small ones--achieves near-perfect agreement, in the range of inter-annotator agreement. In contrast, both multiple choice evaluation and using LLM-as-a-judge without reference answers aligns poorly with human grading. Improving evaluations via answer matching is not merely a conceptual concern: the rankings of several models change significantly when evaluating their free-form responses with answer matching. In light of these findings, we discuss how to move the evaluation ecosystem from multiple choice to answer matching.

In speech enhancement and source separation, signal-to-noise ratio is a ubiquitous objective measure of denoising/separation quality. A decade ago, the BSS_eval toolkit was developed to give researchers worldwide a way to evaluate the quality of their algorithms in a simple, fair, and hopefully insightful way: it attempted to account for channel variations, and to not only evaluate the total distortion in the estimated signal but also split it in terms of various factors such as remaining interference, newly added artifacts, and channel errors. In recent years, hundreds of papers have been relying on this toolkit to evaluate their proposed methods and compare them to previous works, often arguing that differences on the order of 0.1 dB proved the effectiveness of a method over others. We argue here that the signal-to-distortion ratio (SDR) implemented in the BSS_eval toolkit has generally been improperly used and abused, especially in the case of single-channel separation, resulting in misleading results. We propose to use a slightly modified definition, resulting in a simpler, more robust measure, called scale-invariant SDR (SI-SDR). We present various examples of critical failure of the original SDR that SI-SDR overcomes.

We study the feasibility of conducting alignment audits: investigations into whether models have undesired objectives. As a testbed, we train a language model with a hidden objective. Our training pipeline first teaches the model about exploitable errors in RLHF reward models (RMs), then trains the model to exploit some of these errors. We verify via out-of-distribution evaluations that the model generalizes to exhibit whatever behaviors it believes RMs rate highly, including ones not reinforced during training. We leverage this model to study alignment audits in two ways. First, we conduct a blind auditing game where four teams, unaware of the model's hidden objective or training, investigate it for concerning behaviors and their causes. Three teams successfully uncovered the model's hidden objective using techniques including interpretability with sparse autoencoders (SAEs), behavioral attacks, and training data analysis. Second, we conduct an unblinded follow-up study of eight techniques for auditing the model, analyzing their strengths and limitations. Overall, our work provides a concrete example of using alignment audits to discover a model's hidden objective and proposes a methodology for practicing and validating progress in alignment auditing.

We develop a principled procedure for determining when a large language model (LLM) should abstain from responding (e.g., by saying "I don't know") in a general domain, instead of resorting to possibly "hallucinating" a non-sensical or incorrect answer. Building on earlier approaches that use self-consistency as a more reliable measure of model confidence, we propose using the LLM itself to self-evaluate the similarity between each of its sampled responses for a given query. We then further leverage conformal prediction techniques to develop an abstention procedure that benefits from rigorous theoretical guarantees on the hallucination rate (error rate). Experimentally, our resulting conformal abstention method reliably bounds the hallucination rate on various closed-book, open-domain generative question answering datasets, while also maintaining a significantly less conservative abstention rate on a dataset with long responses (Temporal Sequences) compared to baselines using log-probability scores to quantify uncertainty, while achieveing comparable performance on a dataset with short answers (TriviaQA). To evaluate the experiments automatically, one needs to determine if two responses are equivalent given a question. Following standard practice, we use a thresholded similarity function to determine if two responses match, but also provide a method for calibrating the threshold based on conformal prediction, with theoretical guarantees on the accuracy of the match prediction, which might be of independent interest.

Forecasts of explosive AI progress hinge on AI agents automating AI research. But evidence on whether agents can carry out open-ended AI research is thin. Current evaluations either test agents on narrow, verifiable tasks, which excludes open-ended research, or submit AI-generated papers to blind peer review, which is overstretched, stochastic, and suffers from poor review quality. We introduce a third way to measure progress towards AI R\&D automation. An agent takes on the central, open-ended research question of a high-quality unpublished paper, and the paper's original authors grade its output. We call these shadow evaluations. We ran shadow evaluations on two unpublished NeurIPS 2026 submissions, giving frontier agents six days and thousands of dollars of compute. The agents completed all of the engineering without human help, yet could not make substantial progress towards answering the research questions. As a result, both papers were unambiguously rejected by the authors. We identify five recurring failure modes: poor judgment about the bar for publishable research, uncreative responses to shortcomings in the research design, ineffective backtracking from dead ends, poor resource awareness, and instruction drift. A robustness check with a second model and scaffold reproduced these failures. We release the expert reviews, survey responses, agent repositories, and logs. Our results provide early evidence that today's agents can do the engineering of AI research, but struggle with critical parts of the research lifecycle.

AI evaluations are widely used for testing and understanding progress. However, the diverse evaluators bring with them inconsistencies that challenge analysis and comparison. First, results are saved in incompatible formats, scattered across leaderboards, papers, blog posts, evaluation harness logs, and custom repositories. Second, results are created by different evaluation frameworks, which produce divergent scores for nominally identical evaluations and record metadata inconsistently, hindering comparison, cross-community evaluation science, cost reduction, and reuse. We introduce Every Eval Ever, the first shared schema and community-crowdsourced repository for AI evaluation results. The schema standardizes how evaluations are represented in a unified, single JSON document. It is source-agnostic by design, ingesting results from evaluation harnesses and papers alike, and optionally stores per-instance outputs for fine-grained analysis. We contribute: (i) a community-governed metadata schema with a companion instance-level schema, the first standardization effort of its kind; (ii) automatic converters from popular formats, evaluation harnesses, and leaderboards to the unified schema; and (iii) a crowdsourced community database hosted on Hugging Face, currently spanning to date 22,235 models, 2,273 unique benchmarks, and 31 evaluation formats.

What does it mean for an algorithm to be biased? In U.S. law, unintentional bias is encoded via disparate impact, which occurs when a selection process has widely different outcomes for different groups, even as it appears to be neutral. This legal determination hinges on a definition of a protected class (ethnicity, gender, religious practice) and an explicit description of the process. When the process is implemented using computers, determining disparate impact (and hence bias) is harder. It might not be possible to disclose the process. In addition, even if the process is open, it might be hard to elucidate in a legal setting how the algorithm makes its decisions. Instead of requiring access to the algorithm, we propose making inferences based on the data the algorithm uses. We make four contributions to this problem. First, we link the legal notion of disparate impact to a measure of classification accuracy that while known, has received relatively little attention. Second, we propose a test for disparate impact based on analyzing the information leakage of the protected class from the other data attributes. Third, we describe methods by which data might be made unbiased. Finally, we present empirical evidence supporting the effectiveness of our test for disparate impact and our approach for both masking bias and preserving relevant information in the data. Interestingly, our approach resembles some actual selection practices that have recently received legal scrutiny.

We propose a deep bilinear model for blind image quality assessment (BIQA) that handles both synthetic and authentic distortions. Our model consists of two convolutional neural networks (CNN), each of which specializes in one distortion scenario. For synthetic distortions, we pre-train a CNN to classify image distortion type and level, where we enjoy large-scale training data. For authentic distortions, we adopt a pre-trained CNN for image classification. The features from the two CNNs are pooled bilinearly into a unified representation for final quality prediction. We then fine-tune the entire model on target subject-rated databases using a variant of stochastic gradient descent. Extensive experiments demonstrate that the proposed model achieves superior performance on both synthetic and authentic databases. Furthermore, we verify the generalizability of our method on the Waterloo Exploration Database using the group maximum differentiation competition.

Robust benchmarks are crucial for evaluating Multimodal Large Language Models (MLLMs). Yet we find that models can ace many multimodal benchmarks without strong visual understanding, instead exploiting biases, linguistic priors, and superficial patterns. This is especially problematic for vision-centric benchmarks that are meant to require visual inputs. We adopt a diagnostic principle for benchmark design: if a benchmark can be gamed, it will be. Designers should therefore try to ``game'' their own benchmarks first, using diagnostic and debiasing procedures to systematically identify and mitigate non-visual biases. Effective diagnosis requires directly ``training on the test set'' -- probing the released test set for its intrinsic, exploitable patterns. We operationalize this standard with two components. First, we diagnose benchmark susceptibility using a ``Test-set Stress-Test'' (TsT) methodology. Our primary diagnostic tool involves fine-tuning a powerful Large Language Model via k-fold cross-validation on exclusively the non-visual, textual inputs of the test set to reveal shortcut performance and assign each sample a bias score s(x). We complement this with a lightweight Random Forest-based diagnostic operating on hand-crafted features for fast, interpretable auditing. Second, we debias benchmarks by filtering high-bias samples using an ``Iterative Bias Pruning'' (IBP) procedure. Applying this framework to four benchmarks -- VSI-Bench, CV-Bench, MMMU, and VideoMME -- we uncover pervasive non-visual biases. As a case study, we apply our full framework to create VSI-Bench-Debiased, demonstrating reduced non-visual solvability and a wider vision-blind performance gap than the original.

Audio-visual understanding is a rapidly evolving field that seeks to integrate and interpret information from both auditory and visual modalities. Despite recent advances in multi-modal learning, existing benchmarks often suffer from strong visual bias -- where answers can be inferred from visual data alone -- and provide only aggregate scores that conflate multiple sources of error. This makes it difficult to determine whether models struggle with visual understanding, audio interpretation, or audio-visual alignment. In this work, we introduce DAVE (Diagnostic Audio Visual Evaluation), a novel benchmark dataset designed to systematically evaluate audio-visual models across controlled challenges. DAVE alleviates existing limitations by (i) ensuring both modalities are necessary to answer correctly and (ii) decoupling evaluation into atomic subcategories. Our detailed analysis of state-of-the-art models reveals specific failure modes and provides targeted insights for improvement. By offering this standardized diagnostic framework, we aim to facilitate more robust development of audio-visual models. The dataset is released: https://github.com/gorjanradevski/dave

Recent advances in foundation models have enabled AI scientists to automate increasingly complete research workflows, from hypothesis generation and code execution to manuscript preparation. Yet workflow coverage alone does not provide access to the full evidence on which scientific discovery depends. Existing systems typically reason over text, code, labels, or precomputed summaries, leaving scientifically decisive spatial, temporal, cross-channel, and procedural relations unavailable to the agent. We introduce OmniScientist, an end-to-end, omni-modal AI scientist that conducts multidisciplinary research directly from heterogeneous raw evidence. A perception layer and 3 autonomous agents for ideation, experiment, and writeup operate within a deterministic pipeline, allowing observations to shape research questions, experimental decisions, and final claims throughout the research lifecycle. By running idea, rigour, and claim checks in code, the system enforces novelty screening, statistical validity, execution provenance, and numerical traceability. We evaluate OmniScientist on 36 real-data cases spanning 5 discipline families, 4 families of scientific evidence, and modalities including images, signals, audio, video, 3-D structures, trajectories, tables, formulae, and graphs. The system completes the full path from raw data to a compiled manuscript in all 36 cases and achieves a mean overall paper score of 6.3 with the reference reasoning backbone. In paired comparisons against a blind variant that receives only precomputed scalar features, direct perception improves all 7 evaluation dimensions and wins 85% of head-to-head judgments. These results show that lifecycle-wide perception is essential for evidence-grounded scientific discovery and provides a practical path toward broadly capable AI scientists.

Large multimodal models (LMMs) are increasingly adopted as judges in multimodal evaluation systems due to their strong instruction following and consistency with human preferences. However, their ability to follow diverse, fine-grained evaluation criteria remains underexplored. We develop Multi-Crit, a benchmark for evaluating multimodal judges on their capacity to follow pluralistic criteria and produce reliable criterion-level judgments. Covering both open-ended generation and verifiable reasoning tasks, Multi-Crit is built through a rigorous data curation pipeline that gathers challenging response pairs with multi-criterion human annotations. It further introduces three novel metrics for systematically assessing pluralistic adherence, criterion-switching flexibility, and the ability to recognize criterion-level preference conflicts. Comprehensive analysis of 25 LMMs reveals that 1) proprietary models still struggle to maintain consistent adherence to pluralistic criteria--especially in open-ended evaluation; 2) open-source models lag further behind in flexibly following diverse criteria; and 3) critic fine-tuning with holistic judgment signals enhances visual grounding but fails to generalize to pluralistic criterion-level judgment. Additional analyses on reasoning fine-tuning, test-time scaling, and boundary consistency between open-source and proprietary models further probe the limits of current multimodal judges. As a pioneering study, Multi-Crit lays the foundation for building reliable and steerable multimodal AI evaluation.

We consider an online learning problem with one-sided feedback, in which the learner is able to observe the true label only for positively predicted instances. On each round, k instances arrive and receive classification outcomes according to a randomized policy deployed by the learner, whose goal is to maximize accuracy while deploying individually fair policies. We first extend the framework of Bechavod et al. (2020), which relies on the existence of a human fairness auditor for detecting fairness violations, to instead incorporate feedback from dynamically-selected panels of multiple, possibly inconsistent, auditors. We then construct an efficient reduction from our problem of online learning with one-sided feedback and a panel reporting fairness violations to the contextual combinatorial semi-bandit problem (Cesa-Bianchi & Lugosi, 2009, Gy\"{o}rgy et al., 2007). Finally, we show how to leverage the guarantees of two algorithms in the contextual combinatorial semi-bandit setting: Exp2 (Bubeck et al., 2012) and the oracle-efficient Context-Semi-Bandit-FTPL (Syrgkanis et al., 2016), to provide multi-criteria no regret guarantees simultaneously for accuracy and fairness. Our results eliminate two potential sources of bias from prior work: the "hidden outcomes" that are not available to an algorithm operating in the full information setting, and human biases that might be present in any single human auditor, but can be mitigated by selecting a well chosen panel.

Open web-scale pre-training corpora remain concentrated in English, limiting multilingual LLM development. We introduce MultiSynt/MT, an open synthetic parallel corpus with approximately 4.8 trillion target-language tokens across 36 European languages, produced by translating 100 billion high-quality Nemotron-CC tokens with Tower+ and OPUS-MT/HPLT-MT systems. For many medium- and lower-resource European languages, this is the largest openly available pre-training resource. On a broad multilingual benchmark suite, reference LLMs trained on MultiSynt/MT reach the final score of HPLT 2.0, a native-data baseline, using roughly 72% fewer pre-training tokens, and outperform it by approximately 15% relative at a matched 100B-token training budget. Our analyses also identify evaluation blind spots: standard multiple-choice benchmarks miss translation-quality differences that a fluency-sensitive LLM-as-judge evaluation cleanly recovers on the trained LLMs (with no fluency deficit in MultiSynt itself), and Norwegian idiomatic and culturally grounded tasks remain better served by native data. We release the corpus, including row-aligned translations from multiple systems, to support controlled research on multilingual pre-training data and evaluation.

We present a generic framework for creating differentially private versions of any hypothesis test in a black-box way. We analyze the resulting tests analytically and experimentally. Most crucially, we show good practical performance for small data sets, showing that at epsilon = 1 we only need 5-6 times as much data as in the fully public setting. We compare our work to the one existing framework of this type, as well as to several individually-designed private hypothesis tests. Our framework is higher power than other generic solutions and at least competitive with (and often better than) individually-designed tests.

Evaluating generative video models remains an open problem. Reference-based metrics such as Structural Similarity Index Measure (SSIM) and Peak Signal to Noise Ratio (PSNR) reward pixel fidelity over semantic correctness, while Frechet Video Distance (FVD) favors distributional textures over physical plausibility. Binary Visual Question Answering (VQA) based benchmarks like VBench~2.0 are prone to yes-bias and rely on low-resolution auditors that miss temporal failures. Moreover, their prompts target a single dimension at a time, multiplying the number of videos required while still not guaranteeing reliable results. WorldJen addresses these limitations directly. Binary VQA is replaced with Likert-scale questionnaires graded by a VLM that receives frames at native video resolution. Video generation costs are addressed by using adversarially curated prompts that are designed to exercise up to 16 quality dimensions simultaneously. The framework is built around two interlocking contributions. First, A blind human preference study is conducted, accumulating (2,696 pairwise annotations from 7 annotators with 100% pair coverage over 50 of the curated prompts times 6 state-of-the-art video models. A mean inter-annotator agreement of 66.9% is achieved and the study establishes a human ground-truth Bradley-Terry (BT) rating with a three-tier structure. Second, A VLM-as-a-judge evaluation engine using prompt-specific, dimension-specific Likert questionnaires (10 questions per dimension, 47,160 scored responses) judges the videos and reproduces the human-established three-tier BT rating structure independently. The VLM achieves a Spearman hatρ=1.000,~p=0.0014 that is interpreted as tier agreement with the human results. Six focused ablation studies validate the robustness of the VLM evaluation framework.

Recent advances have made long-form report-generating systems widely available. This has prompted evaluation frameworks that use LLM-as-judge protocols and claim verification, along with meta-evaluation frameworks that seek to validate these methods. Many of the meta-evaluations estimate an evaluation quality's by comparing its assessments against human pairwise preferences. Prior work, however, suggests that human pairwise preference may be overly simplistic and can fail to capture nuances of expert expectations. We conduct a case study in meta-evaluation for long-form QA benchmarks using ScholarQA-CS2, a benchmark designed for assessing retrieval-augmented deep-research QA in the scientific domain. We comprehensively validate the benchmark through human pairwise preference judgments, then critically examine the strengths, weaknesses, and confounders of this approach. We show that pairwise preference rankings are best suited for system-level evaluation, while explicit metric-wise annotations and expert annotators are critical for reliable metric-level assessment, with subjectivity remaining a key challenge. Based on our findings, we offer practical guidelines for designing future meta-evaluations that better align evaluation methods, annotator expertise, and reporting practices. By surfacing these methodological challenges, we aim to advance evaluation standards for deep-research systems.

Large Language Models (LLMs) embed sensitive, human-generated data, prompting the need for unlearning methods. Although certified unlearning offers strong privacy guarantees, its restrictive assumptions make it unsuitable for LLMs, giving rise to various heuristic approaches typically assessed through empirical evaluations. These standard evaluations randomly select data for removal, apply unlearning techniques, and use membership inference attacks (MIAs) to compare unlearned models against models retrained without the removed data. However, to ensure robust privacy protections for every data point, it is essential to account for scenarios in which certain data subsets face elevated risks. Prior research suggests that outliers, particularly including data tied to minority groups, often exhibit higher memorization propensity which indicates they may be more difficult to unlearn. Building on these insights, we introduce a complementary, minority-aware evaluation framework to highlight blind spots in existing frameworks. We substantiate our findings with carefully designed experiments, using canaries with personally identifiable information (PII) to represent these minority subsets and demonstrate that they suffer at least 20% higher privacy leakage across various unlearning methods, MIAs, datasets, and LLM scales. Our proposed minority-aware evaluation framework marks an essential step toward more equitable and comprehensive assessments of LLM unlearning efficacy.

Large vision language models (VLMs) report strong accuracy on medical question-answering, yet it remains unclear whether they reason from visual evidence or exploit textual shortcuts. We introduce a counterfactual evaluation framework that decouples visual and textual contributions by substituting input images with controlled surrogates blank, pixel-shuffled, image-absent, and CLIP-retrieved hard negatives and derive a suite of grounding metrics including the Visual Reliance Score (VRS) and Visual Hallucination Rate (VHR). We further introduce CORAL (COntrastive Retrieval-Augmented Learning), a 7B-parameter LoRA fine-tune of Qwen2.5-VL-7B trained with a Contrastive Grounding Objective (CGO) that penalises answer invariance under hard-negative image swaps. On a paired controlled evaluation across four closed-form medical VQA benchmarks (PathVQA, PMC-VQA, SLAKE, VQA-RAD; n=400 total), CORAL improves macro accuracy by +6.7 pp (P(Delta>0)=0.988) and reduces VHR by 8.0 pp (P<0.001) over the matched Qwen2.5-VL-7B base; neither MedVLThinker RL variant achieves a significant gain on either metric. Cross-domain diagnostics further reveal that image substitution costs only <=6.5 pp on medical benchmarks versus 48-61 pp on general-domain tasks, situating the grounding gap that CGO targets. We discuss evaluation limitations openly including train/eval benchmark overlap and underpowered secondary metrics and release our framework, training code, and model weights to support reproducible grounding audits of medical VLMs.

As Large Language Models (LLMs) saturate elementary benchmarks, the research frontier has shifted from generation to the reliability of automated evaluation. We demonstrate that standard "LLM-as-a-Judge" protocols suffer from a systematic Alignment Gap when applied to upper-undergraduate to early graduate level mathematics. To quantify this, we introduce QEDBench, the first large-scale dual-rubric alignment benchmark to systematically measure alignment with human experts on university-level math proofs by contrasting course-specific rubrics against expert common knowledge criteria. By deploying a dual-evaluation matrix (7 judges x 5 solvers) against 1,000+ hours of human evaluation, we reveal that certain frontier evaluators like Claude Opus 4.5, DeepSeek-V3, Qwen 2.5 Max, and Llama 4 Maverick exhibit significant positive bias (up to +0.18, +0.20, +0.30, +0.36 mean score inflation, respectively). Furthermore, we uncover a critical reasoning gap in the discrete domain: while Gemini 3.0 Pro achieves state-of-the-art performance (0.91 average human evaluation score), other reasoning models like GPT-5 Pro and Claude Sonnet 4.5 see their performance significantly degrade in discrete domains. Specifically, their average human evaluation scores drop to 0.72 and 0.63 in Discrete Math, and to 0.74 and 0.50 in Graph Theory. In addition to these research results, we also release QEDBench as a public benchmark for evaluating and improving AI judges. Our benchmark is publicly published at https://github.com/qqliu/Yale-QEDBench.

Randomized controlled trials (RCTs) are the benchmark for causal inference, yet field implementation can deviate. We here present a remote audit - a design-based, preregistrable diagnostic that uses only pre-treatment satellite imagery to test whether assignment is independent of local conditions. The conditional randomization test of the remote audit evaluates whether treatment assignment is more predictable from pre-treatment satellite features than expected under the experiment's registered mechanism, providing a finite-sample valid, design-based diagnostic that requires no parametric assumptions. The procedure is finite-sample valid, honors blocks and clusters, and controls multiplicity across image models and resolutions via a max-statistic. We illustrate with two RCTs: Uganda's Youth Opportunities Program, where the audit corroborates randomization and flags selection and missing-data risks; and a school-based trial in Bangladesh, where assignment is highly predictable from pre-treatment features relative to the stated design, consistent with independent concerns about irregularities. Remote audits complement balance tests, lower early-stage costs, and enable rapid design checks when baseline surveys are expensive or infeasible.

We introduce PerceptionBench, a benchmark specifically designed to evaluate the atomic visual perception capabilities of Multimodal Large Language Models (MLLMs). Existing benchmarks often fail to isolate perception: holistic evaluations conflate perceptual errors with failures in reasoning or domain knowledge, while application-driven benchmarks only cover narrow, fragmented domains shaped by heuristic designs. To address these limitations, PerceptionBench adopts a bottom-up approach: by diagnosing the earliest failure points in the responses of frontier MLLMs across 42 existing benchmarks, we construct an error taxonomy whose perception branch defines ten atomic perceptual capabilities. Guided by this taxonomy, we construct 3,000 verified questions with short, unambiguous answers, each isolating a single capability, with difficulty stemming from perception rather than reasoning or knowledge. Benchmark results across sixteen frontier MLLMs reveal that atomic perception remains largely unsolved---no model reaches 60\% accuracy, perception-related hallucination is the weakest capability on average, and similar overall scores conceal sharply divergent capability profiles. PerceptionBench thus provides a capability-level standard for measuring and diagnosing the visual perception boundaries of MLLMs.

Machine unlearning aims to remove sensitive or undesired data from large language models. However, recent studies suggest that unlearning is often shallow, claiming that removed knowledge can easily be recovered. In this work, we critically examine standard unlearning evaluation practices and uncover key limitations that shake our trust in those findings. First, we show that some evaluations introduce substantial new information into the model, potentially masking true unlearning performance by re-teaching the model during testing. Second, we demonstrate that evaluation outcomes vary significantly across tasks, undermining the generalizability of current evaluation routines. Finally, we find that many evaluations rely on spurious correlations, making their results difficult to trust and interpret. Taken together, these issues suggest that current evaluation protocols may both overstate and understate unlearning success. To address this, we propose two principles for future unlearning evaluations: minimal information injection and downstream task awareness. We validate these principles through a series of targeted experiments, showing how violations of each can lead to misleading conclusions.

Large language models have made significant progress in complex but easy-to-verify problems, yet they still struggle with discovering the unknown. In this paper, we present AlphaResearch, an autonomous research agent designed to discover new algorithms on open-ended problems. To synergize the feasibility and innovation of the discovery process, we construct a novel dual research environment by combining the execution-based verify and simulated real-world peer review environment. AlphaResearch discovers new algorithm by iteratively running the following steps: (1) propose new ideas (2) verify the ideas in the dual research environment (3) optimize the research proposals for better performance. To promote a transparent evaluation process, we construct AlphaResearchComp, a new evaluation benchmark that includes an eight open-ended algorithmic problems competition, with each problem carefully curated and verified through executable pipelines, objective metrics, and reproducibility checks. AlphaResearch gets a 2/8 win rate in head-to-head comparison with human researchers, demonstrate the possibility of accelerating algorithm discovery with LLMs. Notably, the algorithm discovered by AlphaResearch on the ``packing circles'' problem achieves the best-of-known performance, surpassing the results of human researchers and strong baselines from recent work (e.g., AlphaEvolve). Additionally, we conduct a comprehensive analysis of the remaining challenges of the 6/8 failure cases, providing valuable insights for future research.

As large language models (LLMs) continue to advance, reliable evaluation methods are essential particularly for open-ended, instruction-following tasks. LLM-as-a-Judge enables automatic evaluation using LLMs as evaluators, but its reliability remains uncertain. In this work, we analyze key factors affecting its trustworthiness, focusing on alignment with human judgments and evaluation consistency. Using BIGGENBench and EvalBiasBench, we study the effects of evaluation design, decoding strategies, and Chain-of-Tought (CoT) reasoning in evaluation. Our results show that evaluation criteria are critical for reliability, non-deterministic sampling improves alignment with human preferences over deterministic evaluation, and CoT reasoning offers minimal gains when clear evaluation criteria are present.

Some security-development settings require local models that map an objective to an ordered, checkable plan. We present a low-rank decomposition adapter and release a case-disjoint corpus with 24 authored decompositions and 83 derived next-step examples across 24 satellite-security cases. To prevent reference-plan leakage, prompts contain one objective and eight shuffled SPARTA candidates. The evaluation candidate sets are constructed with oracle inclusion of every reference technique, so this study measures selection from a controlled set, not retrieval. On six fixed cases and five decoding seeds, mean scores vary across adapters and prompted Qwen2.5 baselines; a separate greedy check over three adapter training seeds shows non-negligible training variance. A 24-fold greedy leave-one-case-out control at the two compact sizes likewise shows tradeoffs: at 1.5B, adapter precision is 0.583 against 0.480 for two-shot prompting, while recall is 0.586 against 0.660. Case-resampling intervals for adapter precision relative to the strongest prompted baseline cross zero at 1.5B and 7B. The adapter is also substantially more format-compliant, which prevents attributing all score differences to selection. Autoregressive next-step accuracy is 0.08, 0.06, and 0.29 at 0.5B, 1.5B, and 7B. We therefore offer the formulation, leakage-controlled dataset, reproducibility package, and descriptive analysis as a proof of concept, not evidence of a reliable stand-alone decomposition system or a general adapter advantage. A separate diagnostic tests contract reuse.

LLM-as-a-judge panels aggregate votes from multiple models, with the expectation that diverse models yield more reliable evaluations. We develop a framework to measure the true informational value of such panels and quantify how far their reliability falls short of the independent-voting ideal. Testing a panel of 9 frontier LLMs from 7 model families on three natural language inference datasets (each with 100 human annotations per item), we find that the 9 judges effectively provide only about 2 independent votes' worth of information. Roughly three-quarters of the panel's nominal independence is lost because the models make the same mistakes on the same items. The consequences are stark: the panel's actual accuracy falls 8-22 percentage points short of what independent voting would achieve, and the best single judge matches or outperforms the full panel across all conditions. Neither adding more judges nor using smarter aggregation algorithms helps -- established methods close at most 11% of this gap, even with access to the correct answers. We quantify these findings using the Kish effective sample size (n_eff) and a Condorcet null model, and show the deficit is robust across prompt variants, temperatures, chain-of-thought reasoning, and a pairwise preference task (RewardBench). The bottleneck is correlated judges, not the aggregation algorithm, implying that scaling up panels cannot substitute for genuinely independent evaluation.

Although large language models (LLMs) have become transformative, they still make mistakes and can explore unproductive reasoning paths. Self-correction is an important capability for a trustworthy LLM, particularly an autoregressive LLM. While LLMs can identify error in user input, they exhibit a systematic 'Self-Correction Blind Spot' - failing to correct identical error in their own outputs. To systematically study this phenomenon, we introduce Self-Correction Bench, a systematic framework to measure this phenomenon through controlled error injection at three complexity levels. Testing 14 models, we find an average 64.5% blind spot rate. We find multiple evidences that this limitation relates to training data composition: human training demonstrations predominantly show error-free responses rather than error-correction sequences, unlike RL-trained models that learn error correction through outcome feedback. Remarkably, simply appending "Wait" reduces blind spots by 89.3%, suggesting that the capability exists but requires activation. Our work highlights a critical limitation in current LLMs and offers potential avenues for improving their reliability and trustworthiness.

Automatic evaluation with large language models, commonly known as LLM-as-a-judge, is now standard across reasoning and alignment tasks. Despite evaluating many samples in deployment, these evaluators typically (i) treat each case independently, missing the opportunity to accumulate experience, and (ii) rely on a single fixed prompt for all cases, neglecting the need for sample-specific evaluation criteria. We introduce Learning While Evaluating (LWE), a framework that allows evaluators to improve sequentially at inference time without requiring training or validation sets. LWE maintains an evolving meta-prompt that (i) produces sample-specific evaluation instructions and (ii) refines itself through self-generated feedback. Furthermore, we propose Selective LWE, which updates the meta-prompt only on self-inconsistent cases, focusing computation where it matters most. This selective approach retains the benefits of sequential learning while being far more cost-effective. Across two pairwise comparison benchmarks, Selective LWE outperforms strong baselines, empirically demonstrating that evaluators can improve during sequential testing with a simple selective update, learning most from the cases they struggle with.

Evaluations are critical for understanding the capabilities of large language models (LLMs). Fundamentally, evaluations are experiments; but the literature on evaluations has largely ignored the literature from other sciences on experiment analysis and planning. This article shows researchers with some training in statistics how to think about and analyze data from language model evaluations. Conceptualizing evaluation questions as having been drawn from an unseen super-population, we present formulas for analyzing evaluation data, measuring differences between two models, and planning an evaluation experiment. We make a number of specific recommendations for running language model evaluations and reporting experiment results in a way that minimizes statistical noise and maximizes informativeness.

The evaluation of recommender system fairness has become increasingly important, especially with recent legislation that emphasises the development of fair and responsible artificial intelligence. This has led to the emergence of various fairness evaluation measures, which quantify fairness based on different definitions. However, many of such measures are simply proposed and used without further analysis on their robustness. As a result, there is insufficient understanding and awareness of the measures' limitations. Among other issues, it is not known what kind of model outputs produce the (un)fairest score, how the measure scores are empirically distributed, and whether there are cases where the measures cannot be computed (e.g., due to division by zero). These issues cause difficulty in interpreting the measure scores and confusion on which measure(s) should be used for a specific case. This thesis presents a series of papers that assess and overcome various theoretical, empirical, and conceptual limitations of existing recommender system fairness evaluation measures. We investigate a wide range of offline evaluation measures for different fairness notions, divided based on the evaluation subjects (users and items) and for different evaluation granularities (groups of subjects and individual subjects). Firstly, we perform theoretical and empirical analysis on the measures, exposing flaws that limit their interpretability, expressiveness, or applicability. Secondly, we contribute novel evaluation approaches and measures that overcome these limitations. Finally, considering the measures' limitations, we recommend guidelines for the appropriate measure usage, thereby allowing for more precise selection of fairness evaluation measures in practical scenarios. Overall, this thesis contributes to advancing the state-of-the-art offline evaluation of fairness in recommender systems.

Black-box risk scoring models permeate our lives, yet are typically proprietary or opaque. We propose Distill-and-Compare, a model distillation and comparison approach to audit such models. To gain insight into black-box models, we treat them as teachers, training transparent student models to mimic the risk scores assigned by black-box models. We compare the student model trained with distillation to a second un-distilled transparent model trained on ground-truth outcomes, and use differences between the two models to gain insight into the black-box model. Our approach can be applied in a realistic setting, without probing the black-box model API. We demonstrate the approach on four public data sets: COMPAS, Stop-and-Frisk, Chicago Police, and Lending Club. We also propose a statistical test to determine if a data set is missing key features used to train the black-box model. Our test finds that the ProPublica data is likely missing key feature(s) used in COMPAS.

Neural Information Retrieval (NIR) has significantly improved upon heuristic-based IR systems. Yet, failures remain frequent, the models used often being unable to retrieve documents relevant to the user's query. We address this challenge by proposing a lightweight abstention mechanism tailored for real-world constraints, with particular emphasis placed on the reranking phase. We introduce a protocol for evaluating abstention strategies in a black-box scenario, demonstrating their efficacy, and propose a simple yet effective data-driven mechanism. We provide open-source code for experiment replication and abstention implementation, fostering wider adoption and application in diverse contexts.

Retrieval models are often evaluated on partially-annotated datasets. Each query is mapped to a few relevant texts and the remaining corpus is assumed to be irrelevant. As a result, models that successfully retrieve false negatives are punished in evaluation. Unfortunately, completely annotating all texts for every query is not resource efficient. In this work, we show that using partially-annotated datasets in evaluation can paint a distorted picture. We curate D-MERIT, a passage retrieval evaluation set from Wikipedia, aspiring to contain all relevant passages for each query. Queries describe a group (e.g., ``journals about linguistics'') and relevant passages are evidence that entities belong to the group (e.g., a passage indicating that Language is a journal about linguistics). We show that evaluating on a dataset containing annotations for only a subset of the relevant passages might result in misleading ranking of the retrieval systems and that as more relevant texts are included in the evaluation set, the rankings converge. We propose our dataset as a resource for evaluation and our study as a recommendation for balance between resource-efficiency and reliable evaluation when annotating evaluation sets for text retrieval.

Recent observations have underscored a disparity between the inflated benchmark scores and the actual performance of LLMs, raising concerns about potential contamination of evaluation benchmarks. This issue is especially critical for closed-source models and certain open-source models where training data transparency is lacking. In this paper we study data contamination by proposing two methods tailored for both open-source and proprietary LLMs. We first introduce a retrieval-based system to explore potential overlaps between evaluation benchmarks and pretraining corpora. We further present a novel investigation protocol named Testset Slot Guessing (TS-Guessing), applicable to both open and proprietary models. This approach entails masking a wrong answer in a multiple-choice question and prompting the model to fill in the gap. Additionally, it involves obscuring an unlikely word in an evaluation example and asking the model to produce it. We find that certain commercial LLMs could surprisingly guess the missing option in various test sets. Specifically, in the TruthfulQA benchmark, we find that LLMs exhibit notable performance improvement when provided with additional metadata in the benchmark. Further, in the MMLU benchmark, ChatGPT and GPT-4 demonstrated an exact match rate of 52\% and 57\%, respectively, in guessing the missing options in benchmark test data. We hope these results underscore the need for more robust evaluation methodologies and benchmarks in the field.

Recent advances in multi-modal generative models have driven substantial improvements in image editing. However, current generative models still struggle with handling diverse and complex image editing tasks that require implicit reasoning, underscoring the need for a comprehensive benchmark to systematically assess their performance across various reasoning scenarios. Existing benchmarks primarily focus on single-object attribute transformation in realistic scenarios, which, while effective, encounter two key challenges: (1) they largely overlook multi-object interactions as well as game-world scenarios that involve human-defined rules, which are common in real-life applications; (2) they only rely on textual references to evaluate the generated images, potentially leading to systematic misjudgments, especially in complex reasoning scenarios. To this end, this work proposes UniREditBench, a unified benchmark for reasoning-based image editing evaluation. It comprises 2,700 meticulously curated samples, covering both real- and game-world scenarios across 8 primary dimensions and 18 sub-dimensions. To improve evaluation reliability, we introduce multimodal dual-reference evaluation, providing both textual and ground-truth image references for each sample assessment. Furthermore, we design an automated multi-scenario data synthesis pipeline and construct UniREdit-Data-100K, a large-scale synthetic dataset with high-quality chain-of-thought (CoT) reasoning annotations. We fine-tune Bagel on this dataset and develop UniREdit-Bagel, demonstrating substantial improvements in both in-domain and out-of-distribution settings. Through thorough benchmarking of both open-source and closed-source image editing models, we reveal their strengths and weaknesses across various aspects.

Large Language Models (LLMs) are increasingly deployed across diverse domains but often exhibit disparities in how they handle real-life queries. To systematically investigate these effects within various disability contexts, we introduce AccessEval (Accessibility Evaluation), a benchmark evaluating 21 closed- and open-source LLMs across 6 real-world domains and 9 disability types using paired Neutral and Disability-Aware Queries. We evaluated model outputs with metrics for sentiment, social perception, and factual accuracy. Our analysis reveals that responses to disability-aware queries tend to have a more negative tone, increased stereotyping, and higher factual error compared to neutral queries. These effects show notable variation by domain and disability type, with disabilities affecting hearing, speech, and mobility disproportionately impacted. These disparities reflect persistent forms of ableism embedded in model behavior. By examining model performance in real-world decision-making contexts, we better illuminate how such biases can translate into tangible harms for disabled users. This framing helps bridges the gap between technical evaluation and user impact, reinforcing importance of bias mitigation in day-to-day applications. Our dataset is publicly available at: https://huggingface.co/datasets/Srikant86/AccessEval

We introduce CompareBench, a benchmark for evaluating visual comparison reasoning in vision-language models (VLMs), a fundamental yet understudied skill. CompareBench consists of 1000 QA pairs across four tasks: quantity (600), temporal (100), geometric (200), and spatial (100). It is derived from two auxiliary datasets that we constructed: TallyBench (2000 counting images with QA) and HistCaps (515 historical images with bilingual captions). We evaluate both closed-source APIs (OpenAI, Gemini, Claude) and open-source models (Qwen2.5-VL and Qwen3-VL series). Results show clear scaling trends but also reveal critical limitations: even the strongest models consistently fail at temporal ordering and spatial relations, and they often make mistakes in basic counting and geometric comparisons that are trivial for humans. These findings demonstrate that visual comparison remains a systematic blind spot for current VLMs. By providing controlled, diverse, and diagnostic evaluation, CompareBench establishes a foundation for advancing more reliable multimodal reasoning.

Large Language Models (LLMs) are widely used as proxies for human labelers in both training (Reinforcement Learning from AI Feedback) and large-scale response evaluation (LLM-as-a-judge). Alignment and evaluation are critical components in the development of reliable LLMs, and the choice of feedback protocol plays a central role in both but remains understudied. In this work, we show that the choice of feedback protocol for evaluation (absolute scores versus relative preferences) can significantly affect evaluation reliability and induce systematic biases. In the context of LLM-as-a-judge evaluation, we show that pairwise protocols are more vulnerable to distracted evaluation. Generator models can exploit spurious attributes (or distractor features) favored by the LLM judge, resulting in inflated scores for lower-quality outputs. We find that absolute scoring is more robust to such manipulation, producing judgments that better reflect response quality and are less influenced by distractor features. Our results demonstrate that generator models can flip preferences by embedding distractor features, skewing LLM-as-a-judge comparisons and leading to inaccurate conclusions about model quality in benchmark evaluations. Pairwise preferences flip in about 35% of the cases, compared to only 9% for absolute scores. We offer recommendations for choosing feedback protocols based on dataset characteristics and evaluation objectives.

Large language models (LLMs) still produce plausible-sounding but ungrounded factual claims, a problem that worsens in multi-turn dialogue as context grows and early errors cascade. We introduce HalluHard, a challenging multi-turn hallucination benchmark with 950 seed questions spanning four high-stakes domains: legal cases, research questions, medical guidelines, and coding. We operationalize groundedness by requiring inline citations for factual assertions. To support reliable evaluation in open-ended settings, we propose a judging pipeline that iteratively retrieves evidence via web search. It can fetch, filter, and parse full-text sources (including PDFs) to assess whether cited material actually supports the generated content. Across a diverse set of frontier proprietary and open-weight models, hallucinations remain substantial even with web search (approx 30% for the strongest configuration, Opus-4.5 with web search), with content-grounding errors persisting at high rates. Finally, we show that hallucination behavior is shaped by model capacity, turn position, effective reasoning, and the type of knowledge required.

Peer review is a cornerstone of quality control in scientific publishing. With the increasing workload, the unintended use of `quick' heuristics, referred to as lazy thinking, has emerged as a recurring issue compromising review quality. Automated methods to detect such heuristics can help improve the peer-reviewing process. However, there is limited NLP research on this issue, and no real-world dataset exists to support the development of detection tools. This work introduces LazyReview, a dataset of peer-review sentences annotated with fine-grained lazy thinking categories. Our analysis reveals that Large Language Models (LLMs) struggle to detect these instances in a zero-shot setting. However, instruction-based fine-tuning on our dataset significantly boosts performance by 10-20 performance points, highlighting the importance of high-quality training data. Furthermore, a controlled experiment demonstrates that reviews revised with lazy thinking feedback are more comprehensive and actionable than those written without such feedback. We will release our dataset and the enhanced guidelines that can be used to train junior reviewers in the community. (Code available here: https://github.com/UKPLab/arxiv2025-lazy-review)

For Large Language Models (LLMs) to be reliably deployed in both everyday and high-stakes domains, knowing when not to answer is equally critical as answering correctly. Real-world user queries, which can be underspecified, ill-posed, or fundamentally unanswerable, require LLMs to reason about uncertainty and selectively abstain -- i.e., refuse to answer definitively. However, abstention remains understudied, without a systematic evaluation framework for modern LLMs. In this work, we introduce AbstentionBench, a large-scale benchmark for holistically evaluating abstention across 20 diverse datasets, including questions with unknown answers, underspecification, false premises, subjective interpretations, and outdated information. Evaluating 20 frontier LLMs reveals abstention is an unsolved problem, and one where scaling models is of little use. While recent reasoning LLMs have shown impressive results in complex problem solving, surprisingly, we find that reasoning fine-tuning degrades abstention (by 24% on average), even for math and science domains on which reasoning models are explicitly trained. We find that while a carefully crafted system prompt can boost abstention in practice, it does not resolve models' fundamental inability to reason about uncertainty. We release AbstentionBench to foster research into advancing LLM reliability.

Self-play is an effective paradigm for language-model self-evolution, but without guidance, solver performance can plateau or decline across rounds. Unguided methods steer question generation with signals such as difficulty, learnability, or diversity. These signals keep questions challenging and varied but do not specify which unresolved reasoning weaknesses later rounds should target. Guided methods obtain direction from external task resources, including human examples, document corpora, or specified difficulty targets, and therefore rely on task information supplied outside the self-play loop. We show that the needed direction can instead be derived from the solver's own failure history. We introduce DiagEvo, whose diagnostician extracts recurring error causes from this history and stores them in a hierarchical error-cause memory. The memory groups related causes under skill nodes and tracks each as Active or Mastered according to self-consistency on targeted questions. The challenger uses these states and recurrence counts to balance cause-targeted generation with free exploration. Double-confidence filtering retains intermediate-difficulty questions only when the most common solver answer has a clear vote lead. DiagEvo derives its curriculum from information produced during self-play, without external task resources. With the default 4B diagnostician, DiagEvo outperforms every baseline in mean accuracy across all nine benchmarks for each of the three solvers: Qwen3-4B, Qwen3-8B, and OctoThinker-8B. On Qwen3-8B, it reaches 72.3% mean accuracy across five mathematical reasoning benchmarks, 4.5 percentage points above R-Zero. Its mean accuracy across all nine benchmarks is 57.4%, 1.1 percentage points above DARC. Ablations show that the hierarchical error-cause memory and double-confidence filtering both contribute to these gains.

Algorithmic fairness has conventionally adopted the mathematically convenient perspective of racial color-blindness (i.e., difference unaware treatment). However, we contend that in a range of important settings, group difference awareness matters. For example, differentiating between groups may be necessary in legal contexts (e.g., the U.S. compulsory draft applies to men but not women) and harm assessments (e.g., referring to girls as ``terrorists'' may be less harmful than referring to Muslim people as such). Thus, in contrast to most fairness work, we study fairness through the perspective of treating people differently -- when it is contextually appropriate to. We first introduce an important distinction between descriptive (fact-based), normative (value-based), and correlation (association-based) benchmarks. This distinction is significant because each category requires separate interpretation and mitigation tailored to its specific characteristics. Then, we present a benchmark suite composed of eight different scenarios for a total of 16k questions that enables us to assess difference awareness. Finally, we show results across ten models that demonstrate difference awareness is a distinct dimension to fairness where existing bias mitigation strategies may backfire.

Large language models increasingly generate research ideas, yet judging their novelty or feasibility at generation time does not establish whether they anticipate subsequent work. We introduce IdeaForecastBench to evaluate research idea forecasting. Given a community's literature up to a cutoff, a system produces up to five ranked ideas, which are evaluated against later papers. The benchmark comprises 624 rolling episodes across 52 topics, with a fixed retrieve-then-judge protocol and separately reported results from two judges. We compare five history-compression strategies across GPT-4.1, Qwen2.5-7B/14B, and Qwen3.5-9B, together with a learned Mode-Decomposition Forecaster (MDF). Under the primary GPT-4.1-mini judge, Summary improves on Direct in Hit@5 and Precision@5 across all four backbones. Qwen2.5 scores above GPT-4.1, whereas Qwen3.5 scores below it. An outcome-blind assessment finds that Qwen2.5 produces broader forecasts, but does not identify how much breadth contributes to its advantage. Threshold and judge diagnostics further clarify the limits of interpreting realization as precise anticipation. IdeaForecastBench provides a common task for studying which research ideas a community subsequently pursues and how reliably this outcome can be measured.

Employing Large Language Models (LLMs) to assess the quality of generated responses, such as prompting instruct-tuned models or fine-tuning judge models, has become a widely adopted evaluation method. It is also known that such evaluators are vulnerable to biases, such as favoring longer responses. While it is important to overcome this problem, the specifics of these biases remain under-explored. In this work, we qualitatively identify six types of biases inherent in various judge models. We propose EvalBiasBench as a meta-evaluation collection of hand-crafted test cases for each bias type. Additionally, we present de-biasing dataset construction methods and the associated preference dataset OffsetBias. Experimental results demonstrate that fine-tuning on our dataset significantly enhances the robustness of judge models against biases and improves performance across most evaluation scenarios. We release our datasets and the fine-tuned judge model to public.

Visually impaired individuals (VIIs) encounter significant daily challenges due to limited access to visual information. Although Multimodal Large Language Models (MLLMs) have achieved impressive results on general vision and language tasks, their practical utility in real-world blind assistance still remains largely underexplored. To fill this gap, we introduce VIABench, a comprehensive video benchmark specifically designed to evaluate MLLMs in Visually Impaired Assistance scenarios using first-person videos recorded or shared by VIIs themselves. VIABench defines three core tasks, each targeting a distinct requirement in visual assistance. Proactive Reminder: Assesses the model's ability to interpret ongoing video content while proactively anticipating and verbally describing upcoming navigation-critical events; Visual Question Answering (VQA): Evaluates the model's capacity to answer user-posed questions about the environment or objects within the video; Vision-Guided Interaction: Tests context-aware reasoning to accomplish intentional interactions between user and environment. To ensure a robust and fair evaluation, we propose a rigorous benchmarking pipeline that supports both online (real-time) and offline settings. Our experiments demonstrate that current MLLMs still struggle to deliver comprehensive support for VIIs, especially in the Proactive Reminder task, which demands accurate anticipation and real-time responsiveness. We hope VIABench will drive future research toward developing customized MLLMs for real-world assistance, ultimately improving navigation and interaction experiences for visually impaired individuals. Code and data will be released at https://github.com/MCG-NJU/VIABench.

We introduce Sci-VBench, a comprehensive benchmark for evaluating knowledge- and reasoning-intensive video generation across scientific domains. It contains 1,253 expert-annotated examples spanning 60 subjects across four core disciplines: Natural Science, Healthcare, Humanities & Social Sciences, and Engineering. Each example requires models to generate temporally rich videos that demand scientific reasoning and knowledge-grounded synthesis, going beyond surface-level visual plausibility. We further establish a rubric-based evaluation protocol. Our analysis shows that, under this protocol, both non-expert human evaluators and MLLM-as-Judge systems can achieve relatively high agreement with expert judgments, supporting reproducible evaluation at scale. We benchmark 16 frontier proprietary and open-source models and find that, while automatic perceptual-quality scores cluster tightly across systems, performance on Prompt Grounding and Scientific and Causal Correctness varies substantially, with a pronounced proprietary-open-source gap. These findings show that advances in visual realism have not yet translated into reliable modeling of scientific and causal dynamics.

RAG systems are increasingly evaluated and optimized using LLM judges, an approach that is rapidly becoming the dominant paradigm for system assessment. Nugget-based approaches in particular are now embedded not only in evaluation frameworks but also in the architectures of RAG systems themselves. While this integration can lead to genuine improvements, it also creates a risk of faulty measurements due to circularity. In this paper, we investigate this risk through comparative experiments with nugget-based RAG systems, including Ginger and Crucible, against strong baselines such as GPT-Researcher. By deliberately modifying Crucible to generate outputs optimized for an LLM judge, we show that near-perfect evaluation scores can be achieved when elements of the evaluation - such as prompt templates or gold nuggets - are leaked or can be predicted. Our results highlight the importance of blind evaluation settings and methodological diversity to guard against mistaking metric overfitting for genuine system progress.

We release the EARS (Expressive Anechoic Recordings of Speech) dataset, a high-quality speech dataset comprising 107 speakers from diverse backgrounds, totaling in 100 hours of clean, anechoic speech data. The dataset covers a large range of different speaking styles, including emotional speech, different reading styles, non-verbal sounds, and conversational freeform speech. We benchmark various methods for speech enhancement and dereverberation on the dataset and evaluate their performance through a set of instrumental metrics. In addition, we conduct a listening test with 20 participants for the speech enhancement task, where a generative method is preferred. We introduce a blind test set that allows for automatic online evaluation of uploaded data. Dataset download links and automatic evaluation server can be found online.

We respond to the recent paper by Makelov et al. (2023), which reviews subspace interchange intervention methods like distributed alignment search (DAS; Geiger et al. 2023) and claims that these methods potentially cause "interpretability illusions". We first review Makelov et al. (2023)'s technical notion of what an "interpretability illusion" is, and then we show that even intuitive and desirable explanations can qualify as illusions in this sense. As a result, their method of discovering "illusions" can reject explanations they consider "non-illusory". We then argue that the illusions Makelov et al. (2023) see in practice are artifacts of their training and evaluation paradigms. We close by emphasizing that, though we disagree with their core characterization, Makelov et al. (2023)'s examples and discussion have undoubtedly pushed the field of interpretability forward.

Both capability and safety benchmarks rest upon the assumption that the behavior of language models undergoing a test is informative about their behavior in deployment. This assumption can fail, should models infer that they are being evaluated and condition their response on such context. This hypothesis, termed ``evaluation awareness'', has been observed in frontier and open-weight language models alike. We provide a systematic study of this phenomenon, by probing for it across six language models (from four families and three sizes) and three metrics. More precisely, we examine whether (i) being under evaluation is linearly represented within the models' activations space, (ii) it is verbalized in their output tokens (as scored by an LLM-as-judge), and (iii) steering causally affects their behavior. For the open-checkpoint Olmo models, we further test these measures at every training stage. In doing so, we report that evaluation awareness is linearly decodable from the residual streams of every model (best AUROC geq 0.7). By contrast, these representations align only in part with verbalization: their correlations and mutual information are nonzero in some settings, yet vary substantially across models, layers, and readout choices. Nevertheless, steering along probe-derived directions can shift the verbalization scores. Finally, a comparison across the Olmo checkpoints reveals that evaluation awareness is already present within base models, becomes amplified throughout the stages of supervised fine-tuning, and remains stable thereafter---unlike the effects of steering, that grow more pronounced at every successive training stage. These results show the need for evaluations to account for the disjunction between what models represent internally, what they verbalize, and their steering.

Medical vision-language models (VLMs) require confidence that reflects both answer correctness and patient-specific visual evidence. Recent GRPO-based methods optimize verbalized confidence together with answer generation. However, this joint optimization may interfere with answer learning and drive confidence toward near-binary values. Verbalized confidence also provides no explicit assessment of visual support. We therefore separate capability learning from confidence estimation and propose DualRead. DualRead builds on the insight that reliability can be read from the actor's internal states at critical moments in the answering process. It freezes the GRPO-trained actor and combines pre-answer solvability with a post-answer assessment of the generated answer and its visual support. To further assess whether confidence reflects visual grounding, we introduce Counterfactual Confidence Grounding AUC (CCG-AUC). It measures whether confidence decreases when real-image substitution changes the actor from correct to incorrect. Across two VLM backbones and both in- and out-of-distribution medical VQA benchmarks, DualRead improves correctness discrimination and calibration over verbalized confidence while preserving answer accuracy. CCG-AUC reveals whether confidence responds to answer-relevant visual evidence rather than primarily to non-visual cues.

Unrestricted adversarial attacks aim to fool computer vision models without being constrained by ell_p-norm bounds to remain imperceptible to humans, for example, by changing an object's color. This allows attackers to circumvent traditional, norm-bounded defense strategies such as adversarial training or certified defense strategies. However, due to their unrestricted nature, there are also no guarantees of norm-based imperceptibility, necessitating human evaluations to verify just how authentic these adversarial examples look. While some related work assesses this vital quality of adversarial attacks, none provide statistically significant insights. This issue necessitates a unified framework that supports and streamlines such an assessment for evaluating and comparing unrestricted attacks. To close this gap, we introduce SCOOTER - an open-source, statistically powered framework for evaluating unrestricted adversarial examples. Our contributions are: (i) best-practice guidelines for crowd-study power, compensation, and Likert equivalence bounds to measure imperceptibility; (ii) the first large-scale human vs. model comparison across 346 human participants showing that three color-space attacks and three diffusion-based attacks fail to produce imperceptible images. Furthermore, we found that GPT-4o can serve as a preliminary test for imperceptibility, but it only consistently detects adversarial examples for four out of six tested attacks; (iii) open-source software tools, including a browser-based task template to collect annotations and analysis scripts in Python and R; (iv) an ImageNet-derived benchmark dataset containing 3K real images, 7K adversarial examples, and over 34K human ratings. Our findings demonstrate that automated vision systems do not align with human perception, reinforcing the need for a ground-truth SCOOTER benchmark.

Large language models (LLMs) garner significant attention for their unprecedented performance, leading to an increasing number of researches evaluating LLMs. However, these evaluation benchmarks are limited to assessing the instruction-following capabilities, overlooking the fundamental abilities that emerge during the pre-training stage. Previous subjective evaluation methods mainly reply on scoring by API models. However, in the absence of references, large models have shown limited ability to discern subtle differences. To bridge the gap, we propose F-Eval, a bilingual evaluation benchmark to evaluate the fundamental abilities, including expression, commonsense and logic. The tasks in F-Eval include multi-choice objective tasks, open-ended objective tasks, reference-based subjective tasks and reference-free subjective tasks. For reference-free subjective tasks, we devise new evaluation methods, serving as alternatives to scoring by API models. We conduct evaluations on 13 advanced LLMs. Results show that our evaluation methods show higher correlation coefficients and larger distinction than other evaluators. Additionally, we discuss the influence of different model sizes, dimensions, and normalization methods. We anticipate that F-Eval will facilitate the study of LLMs' fundamental abilities.

LLM-as-a-Judge has been widely adopted across various research and practical applications, yet the robustness and reliability of its evaluation remain a critical issue. A core challenge it faces is bias, which has primarily been studied in terms of known biases and their impact on evaluation outcomes, while automated and systematic exploration of potential unknown biases is still lacking. Nevertheless, such exploration is crucial for enhancing the robustness and reliability of evaluations. To bridge this gap, we propose BiasScope, a LLM-driven framework for automatically and at scale discovering potential biases that may arise during model evaluation. BiasScope can uncover potential biases across different model families and scales, with its generality and effectiveness validated on the JudgeBench dataset. It overcomes the limitations of existing approaches, transforming bias discovery from a passive process relying on manual effort and predefined bias lists into an active and comprehensive automated exploration. Moreover, based on BiasScope, we propose JudgeBench-Pro, an extended version of JudgeBench and a more challenging benchmark for evaluating the robustness of LLM-as-a-judge. Strikingly, even powerful LLMs as evaluators show error rates above 50\% on JudgeBench-Pro, underscoring the urgent need to strengthen evaluation robustness and to mitigate potential biases further.

This paper introduces LegalRikai: Open Benchmark, a new benchmark comprising four complex tasks that emulate Japanese corporate legal practices. The benchmark was created by legal professionals under the supervision of an attorney. This benchmark has 100 samples that require long-form, structured outputs, and we evaluated them against multiple practical criteria. We conducted both human and automated evaluations using leading LLMs, including GPT-5, Gemini 2.5 Pro, and Claude Opus 4.1. Our human evaluation revealed that abstract instructions prompted unnecessary modifications, highlighting model weaknesses in document-level editing that were missed by conventional short-text tasks. Furthermore, our analysis reveals that automated evaluation aligns well with human judgment on criteria with clear linguistic grounding, and assessing structural consistency remains a challenge. The result demonstrates the utility of automated evaluation as a screening tool when expert availability is limited. We propose a dataset evaluation framework to promote more practice-oriented research in the legal domain.

Hallucinations in multimodal large language models (MLLMs) -- where the model generates content inconsistent with the input image -- pose significant risks in real-world applications, from misinformation in visual question answering to unsafe errors in decision-making. Existing benchmarks primarily test recognition accuracy, i.e., evaluating whether models can select the correct answer among distractors. This overlooks an equally critical capability for trustworthy AI: recognizing when none of the provided options are correct, a behavior reflecting epistemic humility. We present HumbleBench, a new hallucination benchmark designed to evaluate MLLMs' ability to reject plausible but incorrect answers across three hallucination types: object, relation, and attribute. Built from a panoptic scene graph dataset, we leverage fine-grained scene graph annotations to extract ground-truth entities and relations, and prompt GPT-4-Turbo to generate multiple-choice questions, followed by a rigorous manual filtering process. Each question includes a "None of the above" option, requiring models not only to recognize correct visual information but also to identify when no provided answer is valid. We evaluate a variety of state-of-the-art MLLMs -- including both general-purpose and specialized reasoning models -- on HumbleBench and share valuable findings and insights with the community. By incorporating explicit false-option rejection, HumbleBench fills a key gap in current evaluation suites, providing a more realistic measure of MLLM reliability in safety-critical settings. Our code and dataset are released publicly and can be accessed at https://github.com/maifoundations/HumbleBench.

Evaluating generative foundation models on open-ended multimodal understanding (MMU) and generation (MMG) tasks across diverse modalities (e.g., images, audio, video) poses significant challenges due to the complexity of cross-modal interactions. To this end, the idea of utilizing Multimodal LLMs (MLLMs) as automated judges has emerged, with encouraging results in assessing vision-language understanding tasks. Moving further, this paper extends MLLM-as-a-Judge across modalities to a unified manner by introducing two benchmarks, TaskAnything and JudgeAnything, to respectively evaluate the overall performance and judging capabilities of MLLMs across any-to-any modality tasks. Specifically, TaskAnything evaluates the MMU and MMG capabilities across 15 any-to-any modality categories, employing 1,500 queries curated from well-established benchmarks. Furthermore, JudgeAnything evaluates the judging capabilities of 5 advanced (e.g., GPT-4o and Gemini-2.0-Flash) from the perspectives of Pair Comparison and Score Evaluation, providing a standardized testbed that incorporates human judgments and detailed rubrics. Our extensive experiments reveal that while these MLLMs show promise in assessing MMU (i.e., achieving an average of 66.55% in Pair Comparison setting and 42.79% in Score Evaluation setting), they encounter significant challenges with MMG tasks (i.e., averaging only 53.37% in Pair Comparison setting and 30.05% in Score Evaluation setting), exposing cross-modality biases and hallucination issues. To address this, we present OmniArena, an automated platform for evaluating omni-models and multimodal reward models. Our work highlights the need for fairer evaluation protocols and stronger alignment with human preferences. The source code and dataset are publicly available at: https://urrealhero.github.io/judgeanythingweb/.

How many experimental studies would have come to different conclusions had they been run on larger samples? I show how to estimate the expected number of statistically significant results that a set of experiments would have reported had their sample sizes all been counterfactually increased. The proposed deconvolution estimator is asymptotically normal and adjusts for publication bias. Unlike related methods, this approach requires no assumptions of any kind about the distribution of true intervention treatment effects and allows for point masses. Simulations find good coverage even when the t-score is only approximately normal. An application to randomized trials (RCTs) published in economics journals finds that doubling every sample would increase the power of t-tests by 7.2 percentage points on average. This effect is smaller than for non-RCTs and comparable to systematic replications in laboratory psychology where previous studies enabled more accurate power calculations. This suggests that RCTs are on average relatively insensitive to sample size increases. Research funders who wish to raise power should generally consider sponsoring better-measured and higher quality experiments -- rather than only larger ones.

Large language models (LLMs) are increasingly used as judges to replace costly human preference labels in pairwise evaluation. Despite their practicality, LLM judges remain prone to miscalibration and systematic biases. This paper proposes SCOPE (Selective Conformal Optimized Pairwise Evaluation), a framework for selective pairwise judging with finite-sample statistical guarantees. Under exchangeability, SCOPE calibrates an acceptance threshold such that the error rate among non-abstained judgments is at most a user-specified level α. To provide SCOPE with a bias-neutral uncertainty signal, we introduce Bidirectional Preference Entropy (BPE), which queries the judge under both response positions, aggregates the implied preference probabilities to enforce invariance to response order, and converts the aggregated probability into an entropy-based uncertainty score. Across MT-Bench, RewardBench, and Chatbot Arena, BPE improves uncertainty quality over standard confidence proxies, providing a stronger selection signal that enables SCOPE to consistently meet the target risk level while retaining good coverage across judge scales. In particular, at α= 0.10, SCOPE consistently satisfies the risk bound across all benchmarks and judge scales (empirical risk approx 0.097 to 0.099), while retaining substantial coverage, reaching 0.89 on RewardBench with Qwen-14B and 0.98 on RewardBench with Qwen-32B. Compared to naïve baselines, SCOPE accepts up to 2.4times more judgments on MT-Bench with Qwen-7B under the same target risk constraint, demonstrating that BPE enables reliable and high-coverage LLM-based evaluation.

We present GSM-MC, a multiple-choice (MC) dataset constructed by collecting answers and incorrect predictions on GSM8K from 60 open-source models. Through extensive experiments, we show that LLMs' performance on the MC version of this popular benchmark is strongly correlated with their performance on the original version and is quite robust to distractor choices and option orders, while the evaluation time is reduced by a factor of up to 30. Following similar procedures, we introduce MATH-MC, constructed from MATH, and PythonIO, a new program reasoning MC dataset constructed from HumanEval and MBPP. Experimental results indicate that LLMs' performance on these MC benchmarks leaves much room for improvement. Our data and code are available at https://github.com/Geralt-Targaryen/MC-Evaluation.

In Natural Language Processing (NLP), the Elo rating system, originally designed for ranking players in dynamic games such as chess, is increasingly being used to evaluate Large Language Models (LLMs) through "A vs B" paired comparisons. However, while popular, the system's suitability for assessing entities with constant skill levels, such as LLMs, remains relatively unexplored. We study two fundamental axioms that evaluation methods should adhere to: reliability and transitivity. We conduct extensive evaluation of Elo behaviour, illustrating that individual Elo computations exhibit volatility and delving into the impact of varying the Elo rating system's hyperparameters. We show that these axioms are not always satisfied raising questions about the reliability of current comparative evaluations of LLMs. If the current use of Elo scores is intended to substitute the costly head-to-head comparison of LLMs, it is crucial to ensure the ranking is as robust as possible. Guided by the axioms, our findings offer concrete guidelines for enhancing the reliability of LLM evaluation methods, suggesting a need for reassessment of existing comparative approaches.

The reliability of VLM-as-a-Judge is critical for the automatic evaluation of vision-language models (VLMs). Despite recent progress, our analysis reveals that VLM-as-a-Judge often pays limited attention to the image when making decisions. Instead, they often blindly favor the more informative answer, even when they can recognize it conflicts with the image content. We call this problem informativeness bias, which significantly undermines judge reliability. To address it, we propose BIRCH (Balanced Informativeness and CoRrectness with a Truthful AnCHor), a judging paradigm that first corrects inconsistencies with the image content in candidate answers, and then compares the answers against this corrected version. This shifts the judge's focus from informativeness to image-grounded correctness. Experiments on multiple models and benchmarks show that BIRCH reduces informativeness bias by up to 17%, resulting in performance gains of up to 9.8%. Our work reveals an overlooked but fundamental flaw in current VLM-as-a-Judge systems and highlights the need for more principled designs.

Red-team evaluations of AI models support some claims and not others, and the boundary between the two is calculable rather than merely a matter of judgment. We define the evidential ceiling of an evaluation as the largest factor by which one result can move belief under a fixed testing budget, derive it in closed form for the benchmark null result, and use it to locate that boundary exactly. We find that above a calculable harm rate, a benchmark of modest size certifies a category to a stated evidentiary standard, and a clean sheet is then the stronger of the two possible observations, outweighing a single reproduced failure. Below that rate, no passive benchmark of feasible size provides the specified evidence of safety under the fixed scoring rule and approximately independent trial structure. The crossing between the two regimes has a closed form. The bound is not specific to benchmarks: written in terms of a procedure's hypothesis conditioned elicitation rates, it covers adaptive and automated red teaming as well, and shows that discrimination between the hypotheses rather than attack success is what determines evidential worth. Auditing eight evaluation suites against the boundary, we find that current benchmarks are adequate for high-frequency harm categories and several orders of magnitude short for rare, catastrophic ones. Safety benchmarks are not uninformative. They are informative about a specific and computable set of propositions, and the discipline they need is to state which.

Significant progress has been made in the field of Instruction-based Image Editing Models (IIEMs). However, while these models demonstrate plausible adherence to instructions and strong reasoning ability on current benchmarks, their ability to edit small objects remains underexplored, despite its importance for precise local editing and refining details in both real and generated images. In this paper, we introduce DeepLookEditBench (DLEBench), the first benchmark dedicated to assessing the abilities of IIEMs in editing small-scale objects. Specifically, we construct a challenging testbed comprising 1889 samples across seven instruction types. In these samples, target objects occupy only 1%-10% of the image area, covering complex scenarios such as partial occlusion and multi-object editing. To ensure robust evaluation on this benchmark, we propose an evaluation protocol with refined score rubrics to minimize subjectivity and ambiguity in two criteria: Instruction Following and Visual Consistency. This protocol also introduces a dual-mode evaluation framework (Tool-driven and Oracle-guided Modes) addressing the misalignment between LMM-as-a-Judge and human judgements on DLEBench. Empirical results on 10 IIEMs reveal significant performance gaps in small-scale object editing, highlighting the need for specialized benchmarks to advance this ability.

Interpreting individual neurons or directions in activations space is an important component of mechanistic interpretability. As such, many algorithms have been proposed to automatically produce neuron explanations, but it is often not clear how reliable these explanations are, or which methods produce the best explanations. This can be measured via crowd-sourced evaluations, but they can often be noisy and expensive, leading to unreliable results. In this paper, we carefully analyze the evaluation pipeline and develop a cost-effective and highly accurate crowdsourced evaluation strategy. In contrast to previous human studies that only rate whether the explanation matches the most highly activating inputs, we estimate whether the explanation describes neuron activations across all inputs. To estimate this effectively, we introduce a novel application of importance sampling to determine which inputs are the most valuable to show to raters, leading to around 30x cost reduction compared to uniform sampling. We also analyze the label noise present in crowd-sourced evaluations and propose a Bayesian method to aggregate multiple ratings leading to a further ~5x reduction in number of ratings required for the same accuracy. Finally, we use these methods to conduct a large-scale study comparing the quality of neuron explanations produced by the most popular methods for two different vision models.

Safety benchmarks assume that test-condition behavior predicts deployment behavior, an assumption that fails if models detect evaluation cues and adapt. This opens a gap between benchmark performance and deployment behavior: compliance measured under test conditions becomes an optimistic upper bound that overstates how safely a model behaves once the evaluation harness is removed. We characterize this evaluation awareness through eight experiments across 37 open-weight models and seven families. (i)Detection is moderate and training-driven (24/37 models exceed chance, best AUROC 0.714 vs.0.819 human, with instruction tuning dominating over scale). (ii)Detection shifts safety behavior (hard refusal drops 5.8 percentage points under hypothetical framing, and 21/140 HarmBench framing effects are significant, with compliance rising up to +30 percentage points. (iii)Representations survive behavioral collapse (probes retain AUROC 0.98 under rewrites that drive behavior below chance, and multi-layer steering causally moves three downstream tasks while random controls do not). (iv)These axes are weakly coupled (only 1/15 correlations are significant, the sole robust link being behavioral detection versus framing resistance, ρ=-0.79, p<0.001). We call this gap the benchmark illusion: because detectability, behavioral manifestation, and controllability vary independently, it is multivariate rather than a single number, so no single awareness score is a reliable proxy for deployment safety.

Large language model safeguards decide whether to answer before seeing how an answer will be used. This creates a basic problem for dual-use tasks: the same answer can help an authorized professional or an attacker, while an attacker can imitate a benign request and interaction history. We separate the capability released by the model from the evidence available about downstream use. When that evidence is copyable, we derive the exact worst-case floor on attacker assistance while preserving useful answers. The result yields a safety trilemma: Useful Capability, Reliable Safety, and Open Access cannot coexist. We then show how a trusted credential can complement existing safeguards by adding hard-to-copy information that predicts actual downstream use, and identify the stronger condition needed to eliminate the floor. Evidence from dual-use evaluations, adaptive attacks, and deployed trusted-access programs supports the practical relevance of these conditions.

If AI models can detect when they are being evaluated, the effectiveness of evaluations might be compromised. For example, models could have systematically different behavior during evaluations, leading to less reliable benchmarks for deployment and governance decisions. We investigate whether frontier language models can accurately classify transcripts based on whether they originate from evaluations or real-world deployment, a capability we call evaluation awareness. To achieve this, we construct a diverse benchmark of 1,000 prompts and transcripts from 61 distinct datasets. These span public benchmarks (e.g., MMLU, SWEBench), real-world deployment interactions, and agent trajectories from scaffolding frameworks (e.g., web-browsing agents). Frontier models clearly demonstrate above-random evaluation awareness (Gemini-2.5-Pro reaches an AUC of 0.83), but do not yet surpass our simple human baseline (AUC of 0.92). Furthermore, both AI models and humans are better at identifying evaluations in agentic settings compared to chat settings. Additionally, we test whether models can identify the purpose of the evaluation. Under multiple-choice and open-ended questioning, AI models far outperform random chance in identifying what an evaluation is testing for. Our results indicate that frontier models already exhibit a substantial, though not yet superhuman, level of evaluation-awareness. We recommend tracking this capability in future models.

In critical applications, it is vital for classifiers to defer decision-making to humans. We propose a post-hoc method that makes existing classifiers selectively abstain from predicting certain samples. Our abstaining classifier is incentivized to maintain the original accuracy for each sub-population (i.e. no harm) while achieving a set of group fairness definitions to a user specified degree. To this end, we design an Integer Programming (IP) procedure that assigns abstention decisions for each training sample to satisfy a set of constraints. To generalize the abstaining decisions to test samples, we then train a surrogate model to learn the abstaining decisions based on the IP solutions in an end-to-end manner. We analyze the feasibility of the IP procedure to determine the possible abstention rate for different levels of unfairness tolerance and accuracy constraint for achieving no harm. To the best of our knowledge, this work is the first to identify the theoretical relationships between the constraint parameters and the required abstention rate. Our theoretical results are important since a high abstention rate is often infeasible in practice due to a lack of human resources. Our framework outperforms existing methods in terms of fairness disparity without sacrificing accuracy at similar abstention rates.

As frontier language models increasingly saturate standard QA benchmarks, concerns about data contamination, memorization, and escalating dataset creation costs persist. We propose a debate-driven evaluation paradigm that transforms any existing QA dataset into structured adversarial debates--where one model is given the official answer to defend, and another constructs and defends an alternative answer--adjudicated by a judge model blind to the correct solution. By forcing multi-round argumentation, this approach substantially increases difficulty while penalizing shallow memorization, yet reuses QA items to reduce curation overhead. We make two main contributions: (1) an evaluation pipeline to systematically convert QA tasks into debate-based assessments, and (2) a public benchmark that demonstrates our paradigm's effectiveness on a subset of MMLU-Pro questions, complete with standardized protocols and reference models. Empirical results validate the robustness of the method and its effectiveness against data contamination--a Llama 3.1 model fine-tuned on test questions showed dramatic accuracy improvements (50% -> 82%) but performed worse in debates. Results also show that even weaker judges can reliably differentiate stronger debaters, highlighting how debate-based evaluation can scale to future, more capable systems while maintaining a fraction of the cost of creating new benchmarks. Overall, our framework underscores that "pretraining on the test set is no longer all you need," offering a sustainable path for measuring the genuine reasoning ability of advanced language models.

Large language models (LLMs) now reach expert-level scores on medical licensing exams, encouraging the assumption that high scores imply safe medical judgment while patients increasingly use them for health advice. We show this assumption is fragile: when misleading context is injected into questions that LLMs originally answer correctly, they abandon the correct answer. We call the ability to maintain correct judgment under adversarial context epistemic resilience, and introduce MedMisBench to measure it. MedMisBench contains 10,932 medical question items and 48,889 misleading context-option pairs spanning medical reasoning, agentic capability, and patient-journey evaluation. Across 11 model configurations, mean accuracy falls from 71.1% on original questions to 38.0% under focused misleading context, with 51.5% attack success. The most damaging injections are formal, rule-like fabrications: authority-framed falsehoods reach 69.5% attack success and exception-poisoning claims reach 64.1%. A 14-member clinical panel from 7 countries identified serious potential harm in 38.2% of reviewed cases. MedMisBench exposes a structural blind spot in LLM evaluation in medical settings: existing benchmarks measure what models know, but not whether they preserve correct medical judgment under misleading context.

For many evaluation metrics commonly used as benchmarks for unconditional image generation, trivially memorizing the training set attains a better score than models which are considered state-of-the-art; we consider this problematic. We clarify a necessary condition for an evaluation metric not to behave this way: estimating the function must require a large sample from the model. In search of such a metric, we turn to neural network divergences (NNDs), which are defined in terms of a neural network trained to distinguish between distributions. The resulting benchmarks cannot be "won" by training set memorization, while still being perceptually correlated and computable only from samples. We survey past work on using NNDs for evaluation and implement an example black-box metric based on these ideas. Through experimental validation we show that it can effectively measure diversity, sample quality, and generalization.

Proprietary LMs such as GPT-4 are often employed to assess the quality of responses from various LMs. However, concerns including transparency, controllability, and affordability strongly motivate the development of open-source LMs specialized in evaluations. On the other hand, existing open evaluator LMs exhibit critical shortcomings: 1) they issue scores that significantly diverge from those assigned by humans, and 2) they lack the flexibility to perform both direct assessment and pairwise ranking, the two most prevalent forms of assessment. Additionally, they do not possess the ability to evaluate based on custom evaluation criteria, focusing instead on general attributes like helpfulness and harmlessness. To address these issues, we introduce Prometheus 2, a more powerful evaluator LM than its predecessor that closely mirrors human and GPT-4 judgements. Moreover, it is capable of processing both direct assessment and pair-wise ranking formats grouped with a user-defined evaluation criteria. On four direct assessment benchmarks and four pairwise ranking benchmarks, Prometheus 2 scores the highest correlation and agreement with humans and proprietary LM judges among all tested open evaluator LMs. Our models, code, and data are all publicly available at https://github.com/prometheus-eval/prometheus-eval.

Often, the needs and visual abilities differ between the annotator group and the end user group. Generating detailed diagram descriptions for blind and low-vision (BLV) users is one such challenging domain. Sighted annotators could describe visuals with ease, but existing studies have shown that direct generations by them are costly, bias-prone, and somewhat lacking by BLV standards. In this study, we ask sighted individuals to assess -- rather than produce -- diagram descriptions generated by vision-language models (VLM) that have been guided with latent supervision via a multi-pass inference. The sighted assessments prove effective and useful to professional educators who are themselves BLV and teach visually impaired learners. We release Sightation, a collection of diagram description datasets spanning 5k diagrams and 137k samples for completion, preference, retrieval, question answering, and reasoning training purposes and demonstrate their fine-tuning potential in various downstream tasks.

Recent work found that LLMs are sensitive to a wide range of arbitrary prompt dimensions, including the type of delimiters, answer enumerators, instruction wording, and more. This throws into question popular single-prompt evaluation practices. We present DOVE (Dataset Of Variation Evaluation) a large-scale dataset containing prompt perturbations of various evaluation benchmarks. In contrast to previous work, we examine LLM sensitivity from an holistic perspective, and assess the joint effects of perturbations along various dimensions, resulting in thousands of perturbations per instance. We evaluate several model families against DOVE, leading to several findings, including efficient methods for choosing well-performing prompts, observing that few-shot examples reduce sensitivity, and identifying instances which are inherently hard across all perturbations. DOVE consists of more than 250M prompt perturbations and model outputs, which we make publicly available to spur a community-wide effort toward meaningful, robust, and efficient evaluation. Browse the data, contribute, and more: https://slab-nlp.github.io/DOVE/

Current Vision Language Models (VLMs) remain vulnerable to malicious prompts that induce harmful outputs. Existing safety benchmarks for VLMs primarily rely on automated evaluation methods, but these methods struggle to detect implicit harmful content or produce inaccurate evaluations. Therefore, we found that existing benchmarks have low levels of harmfulness, ambiguous data, and limited diversity in image-text pair combinations. To address these issues, we propose the ELITE benchmark, a high-quality safety evaluation benchmark for VLMs, underpinned by our enhanced evaluation method, the ELITE evaluator. The ELITE evaluator explicitly incorporates a toxicity score to accurately assess harmfulness in multimodal contexts, where VLMs often provide specific, convincing, but unharmful descriptions of images. We filter out ambiguous and low-quality image-text pairs from existing benchmarks using the ELITE evaluator and generate diverse combinations of safe and unsafe image-text pairs. Our experiments demonstrate that the ELITE evaluator achieves superior alignment with human evaluations compared to prior automated methods, and the ELITE benchmark offers enhanced benchmark quality and diversity. By introducing ELITE, we pave the way for safer, more robust VLMs, contributing essential tools for evaluating and mitigating safety risks in real-world applications.

Large Language Models (LLMs) are commonly used as evaluators in various applications, but the reliability of the outcomes remains a challenge. One such challenge is using LLMs-as-judges for direct assessment, i.e., assigning scores from a specified range without any references. We first show that this challenge stems from LLM judge outputs being associated with score range bias, i.e., LLM judge outputs are highly sensitive to pre-defined score ranges, preventing the search for optimal score ranges. We also show that similar biases exist among models from the same family. We then mitigate this bias through contrastive decoding, achieving up to 11.3% relative improvement on average in Spearman correlation with human judgments across different score ranges.

We present AutoBench, a fully automated and self-sustaining framework for evaluating Large Language Models (LLMs) through reciprocal peer assessment. This paper provides a rigorous scientific validation of the AutoBench methodology, originally developed as an open-source project by eZecute S.R.L.. Unlike static benchmarks that suffer from test-set contamination and limited adaptability, AutoBench dynamically generates novel evaluation tasks while models alternately serve as question generators, contestants, and judges across diverse domains. An iterative weighting mechanism amplifies the influence of consistently reliable evaluators, aggregating peer judgments into consensus-based rankings that reflect collective model agreement. Our experiments demonstrate strong correlations with established benchmarks including MMLU-Pro and GPQA (respectively 78\% and 63\%), validating this peer-driven evaluation paradigm. The multi-judge design significantly outperforms single-judge baselines, confirming that distributed evaluation produces more robust and human-consistent assessments. AutoBench offers a scalable, contamination-resistant alternative to static benchmarks for the continuous evaluation of evolving language models.

Existing omni-modal benchmarks attempt to measure modality-specific contributions, but their measurements are confounded: naturally co-occurring modalities carry correlated yet unequal information, making it unclear whether results reflect true modality reliance or information asymmetry. We introduce OMD-Bench, where all modalities are initially congruent - each presenting the same anchor, an object or event independently perceivable through video, audio, and text - which we then systematically corrupt to isolate each modality's contribution. We also evaluate calibrated abstention: whether models appropriately refrain from answering when evidence is conflicting. The benchmark comprises 4,080 instances spanning 27 anchors across eight corruption conditions. Evaluating ten omni-modal models under zero-shot and chain-of-thought prompting, we find that models over-abstain when two modalities are corrupted yet under-abstain severely when all three are, while maintaining high confidence (~60-100%) even under full corruption. Chain-of-thought prompting improves abstention alignment with human judgment but amplifies overconfidence rather than mitigating it. OMD-Bench provides a diagnostic benchmark for diagnosing modality reliance, robustness to cross-modal inconsistency, and uncertainty calibration in omni-modal systems.

We investigate how pair-wise data augmentation techniques like Mixup affect the sample complexity of finding optimal decision boundaries in a binary linear classification problem. For a family of data distributions with a separability constant kappa, we analyze how well the optimal classifier in terms of training loss aligns with the optimal one in test accuracy (i.e., Bayes optimal classifier). For vanilla training without augmentation, we uncover an interesting phenomenon named the curse of separability. As we increase kappa to make the data distribution more separable, the sample complexity of vanilla training increases exponentially in kappa; perhaps surprisingly, the task of finding optimal decision boundaries becomes harder for more separable distributions. For Mixup training, we show that Mixup mitigates this problem by significantly reducing the sample complexity. To this end, we develop new concentration results applicable to n^2 pair-wise augmented data points constructed from n independent data, by carefully dealing with dependencies between overlapping pairs. Lastly, we study other masking-based Mixup-style techniques and show that they can distort the training loss and make its minimizer converge to a suboptimal classifier in terms of test accuracy.

Recent progress in reasoning models suggests that generating plausible attempts for research-level mathematics may be within reach, but verification remains a bottleneck, consuming scarce expert time. We hypothesize that a meaningful solution should contain enough method-level information that, when applied to a neighborhood of related questions, it should yield better downstream performance than incorrect solutions. Building on this idea, we propose Consequence-Based Utility, an oracle-free evaluator that scores each candidate by testing its value as an in-context exemplar in solving related yet verifiable questions. Our approach is evaluated on an original set of research-level math problems, each paired with one expert-written solution and nine LLM-generated solutions. Notably, Consequence-Based Utility consistently outperforms reward models, generative reward models, and LLM judges on ranking quality. Specifically, for GPT-OSS-120B, it improves Acc@1 from 67.2 to 76.3 and AUC from 71.4 to 79.6, with similarly large AUC gains on GPT-OSS-20B (69.0 to 79.2). Furthermore, compared to LLM-Judges, it also exhibits a larger solver-evaluator gap, maintaining a stronger correct-wrong separation even on instances where the underlying solver often fails to solve.

LLM-as-a-judge has become the standard for automated evaluation, but it suffers from high cost, significant latency, and opaque decisions -- limitations that undermine its scalability and reliability. We address these with a simple, efficient alternative: program distillation. Instead of prompting an LLM at the evaluation time, we distill its decision logic into a committee of programs that score candidates directly. These programmatic judges offer transparency, are easily inspected or edited, and eliminate per-sample API costs. Building on this notion, we introduce PAJAMA, a system that synthesizes programs as judges, aggregates their decisions into a joint verdict, and incorporates a fallback mechanism to selectively escalate low-confidence cases to an LLM. Across five datasets and four model families, we show that programmatic judges can match the performance of a 13B-size LLM judge. When using program outputs as routing signals, PAJAMA improves both accuracy and throughput and advances the Pareto frontier. Beyond evaluation, programmatic judges produce cheap and effective reward signals: on RewardBench, a reward model distilled from programs' verdicts outperforms one trained on a proprietary LLM's labels at two orders of magnitude lower API cost.

Retrieval-Augmented Generation (RAG) effectively reduces hallucinations in Large Language Models (LLMs) but can still produce inconsistent or unsupported content. Although LLM-as-a-Judge is widely used for RAG hallucination detection due to its implementation simplicity, it faces two main challenges: the absence of comprehensive evaluation benchmarks and the lack of domain-optimized judge models. To bridge these gaps, we introduce Bi'an, a novel framework featuring a bilingual benchmark dataset and lightweight judge models. The dataset supports rigorous evaluation across multiple RAG scenarios, while the judge models are fine-tuned from compact open-source LLMs. Extensive experimental evaluations on Bi'anBench show our 14B model outperforms baseline models with over five times larger parameter scales and rivals state-of-the-art closed-source LLMs. We will release our data and models soon at https://github.com/OpenSPG/KAG.

Ambient AI scribes draft clinical notes under the reassurance that a clinician signs every note. We audited three commercial AI scribes on the same 142 consultations: 565 notes from recorded UK primary-care and US ambulatory encounters plus authored scenarios. Twelve discovery passes proposed 13,678 candidate errors; the 5,898 clearing an importance filter went to an adversarial panel of two models from different families, each told to refute what it could, and 618 survived. One note in three (31.3% [27.0, 35.6]) carries a verified failure, concentrated in allergy and medication information, invented patient identity, and history written up as examination on telephone consultations that can contain none. No product was given a patient record; setting aside the two classes a record would have prefilled, invented identity and dates, the rate is 24.8% [20.8, 29.0]. One failure mode did not fit our scheme, drawn from published scribe-error taxonomies: a treatment the clinician retracts, recorded as delivered care. Two clinicians adjudicated blind, disjoint samples: a physician author upheld 20 of 21 findings (95.2% [77.3, 99.2]) and an independent clinician, not an author, 12 of 12 ([75.8, 100]); both judged every sampled refusal genuine. A failure rate depends on the instrument as much as the scribes. With model, evidence and settings fixed, the review instruction alone moves the share of candidates verified from 9.3% to 79.0%, and the reviewing family moves it too: alone at that instruction the gentler flags 54.8% of notes against 27.8%. Between 28% and 97% of sampled notes carry a failure depending on the standard. Published audits disagree among themselves by a margin instrument differences alone can produce: omission is 54-86% of their errors against our 23.1%. We release all 618 findings with transcript-side evidence, every prompt and model version, and the re-runnable pipeline.

Large language models (LLMs) are widely used as reference-free evaluators via prompting, but this "LLM-as-a-Judge" paradigm is costly, opaque, and sensitive to prompt design. In this work, we investigate whether smaller models can serve as efficient evaluators by leveraging internal representations instead of surface generation. We uncover a consistent empirical pattern: small LMs, despite with weak generative ability, encode rich evaluative signals in their hidden states. This motivates us to propose the Semantic Capacity Asymmetry Hypothesis: evaluation requires significantly less semantic capacity than generation and can be grounded in intermediate representations, suggesting that evaluation does not necessarily need to rely on large-scale generative models but can instead leverage latent features from smaller ones. Our findings motivate a paradigm shift from LLM-as-a-Judge to Representation-as-a-Judge, a decoding-free evaluation strategy that probes internal model structure rather than relying on prompted output. We instantiate this paradigm through INSPECTOR, a probing-based framework that predicts aspect-level evaluation scores from small model representations. Experiments on reasoning benchmarks (GSM8K, MATH, GPQA) show that INSPECTOR substantially outperforms prompting-based small LMs and closely approximates full LLM judges, while offering a more efficient, reliable, and interpretable alternative for scalable evaluation.

Inasmuch as the removal of refusal behavior from instruction-tuned language models by directional abliteration requires the extraction of refusal-mediating directions from the residual stream activation space, and inasmuch as the construction of the contrast baseline against which harmful prompt activations are compared has been treated in the existing literature as an implementation detail rather than a methodological concern, the present work investigates whether a topically matched contrast baseline yields superior refusal directions. The investigation is carried out on the Qwen~3.5 2B model using per-category matched prompt pairs, per-class Self-Organizing Map extraction, and Singular Value Decomposition orthogonalization. It was found that topic-matched contrast produces no functional refusal directions at any tested weight level on any tested layer, while unmatched contrast on the same model, same extraction code, and same evaluation protocol achieves complete refusal elimination on six layers. The geometric analysis of the failure establishes that topic-matched subtraction cancels the dominant activation component shared between harmful and harmless prompts of the same subject, reducing the extracted direction magnitude below the threshold at which weight-matrix projection perturbs the residual stream. The implications for the design of contrast baselines in abliteration research are discussed.

Ambient AI scribes draft clinical notes, and published audits find their dominant error is omission: information the encounter established that the note fails to record. The standard check is an LLM judge: a second model reads the note against the transcript and flags problems. We ask whether judges detect omissions. Public corpora cannot supply the answer key: their clinician reference notes and transcripts are materially discrepant. Our benchmark has 500 single-error note pairs from audited fact sheets, 298 with a named fact certainly absent and 202 added-or-altered controls. Across eight judge designs, paired discrimination (the flawed note below its clean twin, 0.5 a coin flip) reads 0.79-0.94 on added or altered content and 0.50-0.63 on omissions. On single notes, no design flags omissions reliably more often than perfect notes. Wording changes, voting and GEPA prompt optimisation move the operating point without creating usable detection. Restructuring the task recovers it: list the facts the transcript establishes, then check the note for each. Two methods reach it independently and trade off: a per-fact pipeline, and a GEPA-evolved prompt doing the same in one call. The pipeline's flags name the missing fact and its severity at 2.7% false alarms. The single call detects more (36.9% against 24.6%, p=0.002) at 6.2% false alarms and a tenth of the cost per note. A physician author validated 70 items and, where the two routes disagree, sided with the pipeline on 10 of 10 (p=0.002). A second clinician, not an author, graded the severity rubric blind and agrees to within a grade. On real vendor notes from a companion census no benchmark threshold transfers, but the re-calibrated single call detects more than the best of the eight at half its false-alarm rate. Omissions whose fact is restated elsewhere defeat both routes. We release the benchmark, prompts and judgements.