LLM-as-a-Judge

Background: LLM judges increasingly score whether clinical language models give overconfident answers under incomplete evidence, yet whether a measured "safety gain" reflects real behavior change or the judge's calibration is unresolved. Using a structured evidence-sufficiency prompt as a test case, we asked whether it reduces unsafe overconfident answers, how far that effect depends on the scoring judge, and what it costs in helpfulness. Methods: In a retrospective public-data benchmark (Real-POCQi, HealthBench, MedRBench), four models (GPT-5.5, Claude Opus 4.8, Gemini 3.5 Flash, Grok 4.3) answered a fully paired common panel (1,200 cells) with a standard prompt and the wrapper. The pre-specified endpoint was the paired reduction in unsafe overconfidence scored by the primary judge (GPT-5.4-nano); secondary analyses added a different-family judge (Claude Sonnet 5), a correctness judge, matched scaffold controls, and a blinded three-clinician review. Results: Unsafe overconfidence fell from 49.3% to 24.7%, a paired reduction of 24.7 points (95% CI 21.8-27.7; p<0.001), robust in direction across models and paraphrases. Magnitude was judge-dependent: Sonnet agreed on direction but nearly halved the effect (+13.1 points), with one-directional disagreement. Blinded clinicians characterized the primary judge as a high-sensitivity (1.00), low-specificity (0.55) screen, not a calibrated rate. The gain carried a model-specific helpfulness cost (correct diagnosis 80.3% to 50.3%): near-free for GPT-5.5, near-total for Gemini (-58 points). Matched scaffold controls showed genuine behavior change, not judge circularity. Conclusions: LLM-judged clinical safety effects should be reported as directional and relative, anchored to human review and evaluated jointly with helpfulness, not as calibrated absolute rates. This does not establish clinical deployment readiness.

Large language models (LLMs) are increasingly adopted for network automation, yet their output quality and inference cost can vary substantially across LLM families. We present HuGLEN, a stepwise evaluation pipeline that uses an LLM-as-a-judge together with a small set of expert ratings to enable scalable and reproducible comparison of candidate LLMs, and to rank them using a quality efficiency score (QES). We demonstrate HuGLEN for translating outputs from an explainable artificial intelligence (XAI) model for the optical network quality of transmission (QoT) estimation task into operator-friendly explanations. Our results show that a medium-sized LLM (12B parameters) achieves the highest QES, indicating the best trade-off between explanation quality and efficiency. Overall, HuGLEN reduces the human-labeling burden while supporting consistent model selection for operator-facing automation tasks.

The value alignment of large language models (LLMs) is crucial for ensuring responses align with human intention and value preferences. However, most evaluations of value alignment focus on Western or universal values, while assessments grounded in the value systems of specific countries remain scarce. In this paper, we introduce Pancasila-Dilemmas, an evaluation dataset of 1,834 questions derived from Indonesian news, classified by 5 values of Pancasila: Religion, Humanity, Unity, Democracy, and Social Justice. This dataset reflects daily life in Indonesia, making it suitable for measuring the value alignment of LLMs deployed for Indonesia. To ensure a more rigorous evaluation, we choose scenarios containing dilemmas. The dataset is proofread by native speakers and answered by 5 diverse Indonesian citizens. We evaluate 50 closed- and open-source LLMs on our dataset. Results reveal that all evaluated LLMs achieves less than 0.5 Probability Match Score (PMS) and 0.72 Max-Vote Agreement Score (MVAS). Compared by each values, LLMs mostly struggle in Religion and Unity dilemma cases. This highlights a significant gap in capturing Indonesian values. The dataset is publicly available at https://github.com/tjunlp-lab/Pancasila-Dilemmas.

Concept erasure aims to remove semantic concepts from a trained generative model and is increasingly important for responsible AI deployment. However, verifying whether a model has robustly removed targeted concepts remains a critical challenge. Existing evaluation methods are typically pre-defined and static, failing to expose vulnerabilities under diverse natural-language probes and challenging conditions. Moreover, manually designed evaluation strategies can be biased and difficult to scale. We posit that concept erasure evaluation is best formulated as an adaptive hypothesis search, operationalised by agents that iteratively propose, critique, and verify tests to systematically expand coverage of failure modes. To this end, we propose Stress Testing Agents for Concept Erasure (STACE), a framework that autonomously stress-tests concept-erased models using multiple Large Language Model (LLM) agents, by iteratively generating and verifying stress-testing hypotheses grounded by external knowledge. We also introduce a suite of metrics for assessing the performance and efficiency of LLM-agent-powered stress-testing frameworks. Our extensive experiments show that STACE outperforms five LLM-based evaluation baselines on four concept categories. Further analysis across two T2I models, six concept erasure approaches, and various erasure strengths show that STACE is robust for different settings. We also show that STACE can be adapted beyond concept erasure evaluation to other problem domains, such as LLM jailbreaking. Our code is available anonymously.

The assessment of jailbreak attacks against large language models currently suffers from inconsistent evaluation criteria and methods, leading to unreliable estimates of attack success rates. We propose JailMeter, an evidence-based evaluation framework designed to more faithfully measure jailbreak effectiveness. Inspired by the Information Bottleneck theory, JailMeter applies dual-feedback optimization to filter jailbreak noise from model responses while preserving content relevant to the original malicious question. This process produces concise evidence for a rigorous assessment under which an attack is validated only when the response captures the malicious intent and delivers a complete answer, thereby signaling a substantive bypass of model safety alignment. We evaluate JailMeter on JailMeter-Eva, a challenging benchmark containing 330 human-labeled, non-rejected jailbreak instances. JailMeter achieves an accuracy of 97.27%, substantially outperforming existing evaluation methods. To support large-scale evaluation, we further distill JailMeter into a small language model, JailMeter\textsubscript{SLM}, which maintains comparable reliability with significantly reduced computational costs. Code and dataset are available at https://github.com/Magi2B0y/JailMeter.

Traditional benchmarks for LLMs primarily rely on static datasets and objective scoring metrics, which often fail to capture differences in response quality when multiple answers are acceptable. In such settings, correctness alone is insufficient to distinguish between responses that vary in clarity, completeness, and usefulness. This paper introduces a consensus-based evaluation framework that measures relative preference among model-generated responses rather than absolute correctness. Instead of evaluating outputs against a fixed ground truth, we assess how a panel of diverse LLMs ranks anonymized candidate responses to the same prompt. This approach treats aggregate inter-model agreement as a proxy for perceived response quality under blind conditions. We conduct a controlled study using five state-of-the-art LLMs across multiple domains, including programming, general knowledge, safety, logical reasoning, and mathematics. Each model generates responses and independently ranks peer outputs through a structured voting process. Scores are aggregated into a Relative Intelligence Index (RII), representing how frequently a model's responses are preferred by other models. Our findings reveal consistent preference patterns across domains, with certain models more frequently ranked highly by their peers. However, we emphasize that these results reflect inter-model preference alignment rather than objective correctness or human judgment. This framework provides a scalable, model-driven method for comparative evaluation, offering an alternative perspective on response quality in scenarios where multiple valid answers exist. While not directly aligned with human evaluation, prior work suggests that aggregated model preferences can partially correlate with human judgments, motivating this as a proxy signal.

Long-term memory is becoming a core component of LLM agents, but most memory benchmarks evaluate conversations or compact summaries, while research agents need to restore evidence from full scientific papers. We introduce two full-text scientific-memory benchmarks, Public AI Memory (PAIM; 81 papers, 66 questions) and Public Transformers (PTr; 252 papers, 98 questions). We evaluate eight memory/retrieval systems, including our own proposed Theoria, plus a no-retrieval baseline. Our results show that memory leaderboards are not interpretable without the full protocol: ingestion granularity, raw-text preservation, retrieval budget, retrieval modality, rubric audit, and judge choice all affect the outcome. For example, on PAIM Graphiti wins convincingly but uses 2.6M characters of retrieved context per query, and after controlling for retrieval budget the lead disappears. On PTr, for the systems where BM25 retrieval can be added cleanly, the sparse-dense hybrid is the single most significant intervention: hybrid variants of Simple RAG, Mem0, and Theoria tie for the lead within 0.03 points. Multi-judge and human side-by-side calibration show that LLM-as-a-judge rankings are consistent across frontier judges and agree with human evaluation, with an effective resolution of roughly one point on a ten-point scale. We argue that scientific memory should be evaluated as budgeted, modality-aware context restoration rather than as an unconstrained architecture leaderboard, and we release the datasets, harness, raw outputs, judgments, and scripts to reproduce our results and serve as tools for such evaluation. Our code is available at http://gitlab.com/quantellence/research/scientific-recall-bench , and the datasets are available at http://huggingface.co/datasets/quantellence/srb-data .

We present TellTale, a text-only approach to ambivalence/hesitancy (A/H) recognition in interview videos, evaluated on the BAH dataset as part of the 3rd A/H Video Recognition Challenge (11th ABAW Workshop, ECCV 2026). Although the dataset provides video, audio, facial crops, and transcripts, TellTale relies on the transcript alone and combines three probability streams. Two text encoders, multilingual-e5-large and mDeBERTa-v3-base, are fine-tuned with parameter-efficient LoRA adapters under a multiple-instance learning (MIL) objective, in which transcript chunks are scored individually and pooled with a smooth maximum so that only the video-level label is needed for supervision. The third stream requires no training: a quantized 14B instruction LLM is prompted, zero-shot, to rate each transcript for A/H. The three probabilities are combined by a weighted average and a single decision threshold, both selected on participant-grouped cross-validated predictions. On the organizer-scored private test set of 152 videos from unseen participants, TellTale achieves a Macro-F1 of 0.7364 and an average precision of 0.7940, compared with 0.2827 Macro-F1 for the official vision-based baseline.

Evaluations should do more than measure a models current performance. They should tell us what to fix for the next model iteration and provide a way to generate targeted post training data. Most evaluation pipelines identify weak examples, topics, or categories, but they leave the underlying capability failure implicit: they say where a model fails, not why. We introduce CRAFT, a method that converts any rubric based evaluation dataset into a model specific diagnosis of weak capabilities. CRAFT treats each grading criterion as a capability probe: it extracts a capability description from every prompt rubric pair, clusters these descriptions into a hierarchical capability tree, scores the target model at every node, and selects low performing nodes dynamically across tree levels, at the granularity where each failure is clearest. The selected weak capabilities then direct the generation of targeted supervised finetuning data. Holding the data generation, finetuning, and evaluation setup fixed, we compare CRAFT against prompt level EvalTree clustering and untargeted random generation on four open source models, two professional domains (finance and legal), and 13 held out benchmarks disjoint from the diagnostic data. CRAFT achieves the strongest finance domain average for all four models under repeated temperature decoding; on legal domain, it is strongest for three of four models and remains within the decoding variance bands of the best baseline on the fourth. Diagnosing weaknesses at the level of rubric criteria, rather than prompts or categories, thus yields both a sharper picture of what a model cannot do and measurably better models after finetuning on that diagnosis.

While instruction-based video editing has advanced rapidly, real-world videos contain tightly coupled audio and visual signals, and editing one modality often requires coordinated changes in the other. Existing benchmarks primarily evaluate visual transformations on silent clips or isolated audio editing, leaving complex audio-visual editing and cross-modal consistency underexplored. We introduce AVE-Compass, a comprehensive benchmark with 145 curated source videos, 196 audio-visually coupled editing instructions, and 2,688 fine-grained checklist items. It evaluates Instruction Following, Fidelity Preserving, Realism, and Editing Intent through checklist-based MLLM judging and a dedicated realism rubric, complemented by automated cross-modal, video, and audio metrics. Extensive evaluation shows that state-of-the-art models still struggle to execute cross-modal instructions while preserving non-target content. We further propose AVE-Agent, a modular agent framework that decomposes complex instructions into dependent subtasks and iteratively improves editing results through self-reflection and evaluator feedback. AVE-Agent improves instruction execution, Fidelity Preserving, and audio-visual alignment in joint editing while maintaining competitive perceptual quality.

Geospatial datasets support applications from urban planning to climate modeling, yet consistent assessment of FAIR compliance is difficult. Existing evaluators use different rubrics and evidence sources and may fail on JavaScript-rendered pages or repository-specific identifiers. For 50 datasets from 10 repositories, the standard deviation of normalized scores across available tools averages 15.0 percentage points and reaches 30.3 for one dataset. Because these outputs are not equivalent measurements, we use them to characterize disagreement and failure modes, not comparative accuracy. We present AgentFAIR, a multi-agent framework combining structured metadata extraction with 13 sub-principle-specific LLM evaluators. Each produces a 0-3 maturity score, cited evidence, and recommendations; a critic checks evidence and consistency and can request targeted re-evaluation. Mean Findability, Accessibility, Interoperability, and Reusability scores are 79.7%, 70.4%, 45.3%, and 72.0%. Rank correlations with four baseline tools range from 0.31 to 0.61; the FAIR-enough comparison is not statistically significant. On a 10-dataset repeated-run subset, sub-principle agreement averages 89% (standard deviation: 3 percentage points), versus 71% without the critic. A preliminary 15-dataset expert study yields Fleiss' kappa of 0.71 and 82% alignment with expert consensus. API cost is approximately USD 0.054 per dataset. These results support auditability and feasibility, while the limited benchmark, incomplete ablations, and single-model-family validation constrain claims about accuracy and generalization.

Probably not, at least for meta-analyses in economics. In a pre-registered, identity-masked, within-paper experiment, the authors of 44 meta-analyses ranked three AI reports on their own paper by usefulness for improving it: a single pass by a frontier model against two multi-agent debate tools we built and expected to win. All reports were held to a common length and template. The authors preferred the single pass, by 0.66 rank points over mad-research (95% CI 0.32 to 1.00) and 0.57 over paper-workshop (0.16 to 0.95), though paper-workshop spent roughly thirty times the tokens. Authors who recalled their journal referee report usually placed it first and never last; in a separate exercise, three AI judges almost always placed the real journal referee report last. Among the three AI reports, Gemini (the judge whose model family wrote none of the reports) would have ranked paper-workshop first in the authors' place, reversing the single-pass preference. The reversal warns against substituting an AI judge for the author. We measure perceived usefulness for finished papers; whether AI should referee papers is a separate question.

Large language models routinely produce fluent answers to single-shot prompts, yet deploying them as reliable components of a domain decision system is substantially harder. Closing this gap is the work of harness engineering: the deliberate composition of deterministic scaffolding (symbolic filters, retrieval, schema-typed I/O, LLM-as-judge loops, HITL gates, persistent state, audit trails) around an LLM core. We present a case study in academic supervision, a domain combining high-stakes recommendation, longitudinal accountability, and structured operational workflows. We compare a baseline (ASA), a GPT-5 chatbot with no scaffolding, against a multi-module system (ASuS) that wraps the much smaller GPT-4o-mini in a LangGraph harness with symbolic-semantic retrieval, schema-validated outputs, LLM-as-judge with bounded retry, HITL gates, deterministic weighted risk scoring with LLM narration, and a per-node SQLite audit trail. The evaluation rubric is retargeted at six harness-mechanism dimensions (grounding, explainability, consistency, process integrity, cognitive load, constraint adherence). A blind ten-rater hybrid evaluation, supplemented by a 2 x 2 model-harness ablation, finds that ASuS, despite using a much smaller base model, outscores ASA on every dimension. Across ten raters the pooled mean for ASuS is 4.08 versus 1.23 for ASA, and 8 of 10 raters reject the null at alpha = 0.05 on a paired Wilcoxon test; full numbers are in Sections 6.4 and 6.7. The ablation confirms that the structural contributions of the harness are largely model-invariant. We extract seven recurring harness-engineering patterns and argue that where reliability, traceability, and institutional consistency matter more than open-ended fluency, harness engineering challenges the prevailing 'bigger model is better' intuition.

This study examines feedback in English as a Foreign Language (EFL) writing contexts, focusing on written corrective feedback (WCF). Large language models (LLMs) can provide WCF at scale, but aligning them with pedagogical best practices remains an ongoing challenge. WCF meeting criteria like factuality or relevance may still be unsuitable for learning contexts, highlighting the need for extrinsic evaluation based on the learner's perspective. We deployed WCF systems in a university-level EFL class with nearly 2,000 students, collecting over 20,000 drafts. We evaluated the generated WCF from two perspectives: intrinsic evaluation by experienced English teachers using a rubric, and extrinsic evaluation via student feedback and engagement metrics. Results revealed low alignment between teacher expert ratings and student feedback. These findings suggest that traditional expert evaluation alone may not fully capture WCF's usability or helpfulness from the learner's perspective, highlighting the importance of learner-centered evaluation frameworks for AI-based applications in language education.

Multi-modal Large Language Models (MLLMs) have made substantial advances on benchmarks, yet their real-world effectiveness remains uncertain. This gap stems from the fundamental misalignment between benchmarks in controlled, static settings and the dynamic, interactive, and contextualized nature of real-world applications. To bridge this gap, we propose CEDI (Contextualized Evaluations of MLLMs through Dynamic, multi-round Interactions), a framework that recasts evaluation as a three-party interaction between an evaluatee model, an automated examiner, and a grader. The examiner conducts multi-turn, semi-structured conversation guided by a graph-based representation of the task. By navigating state-space transitions, CEDI deploys diverse strategies, from clarification requests to adversarial probes, to elicit performance evidence. We apply CEDI to visual hallucinations. Empirical results across multiple models, diverse settings, datasets, and domains show that contextualized, interactive evaluations reveal not only significantly more hallucinations than conventional static evaluation but also ones that more closely resemble those arising in practical use cases. We further show that hallucinations often accumulate over long contexts, through self-reinforcing dialogue history, and models are particularly vulnerable to questions requiring premise rejection or refusal. Together, these findings highlight CEDI as a step toward realistic, systematic, and ecologically valid assessments of MLLMs' capabilities. Code is available at github.com/williamium3000/cedi.

LLM evaluators (trained reward models and prompted LLM-as-a-Judge) are routinely validated via pairwise accuracy. In a multilingual setting, this operates under the premise that high pairwise accuracy implies reliable, language-neutral scoring. We show that this assumption does not hold. We conduct experiments with semantically identical instruction-response pairs across 23 languages, and find that multilingual evaluators assign significantly different scores to different evaluation languages. The bias is statistically significant and consistent across eight open-weight evaluators of different architectures and training paradigms, persists in frontier judges, and is strongly correlated with language resource level: lower-resource languages are scored more generously. Meanwhile, these biases are invisible to pairwise accuracy: evaluators achieve above 90% pairwise accuracy, yet have up to 43% difference in acceptance rate across languages under a global decision threshold, meaning, for instance, that harmful content in lower-resource languages is more likely to pass safety filters. Per-language thresholds would require language identification, which can be defeated by code-switched prompts. We then investigate why lower-resource languages receive higher rather than lower scores, and we find that model uncertainty is linked with the effect: models tend to give higher scores when less confident, both under negative log-likelihood and under token-free uncertainty measures; however, language identity remains a significant predictor after controlling for uncertainty, and the bias cannot be explained away by content difficulty alone, but is a structural, language-level misalignment.

The rapid development of Large Language Models (LLMs) and Artificial Intelligent (AI) powered autonomous agents has fundamentally changed the existing forms of software governance. In spite of the rigorous standards of transparency and account ability required according to the international frameworks such as the European Union's AI Act, there is a considerable gap between theory and reality. The present study discusses the inherent drawbacks of currently utilized platforms for LLM evaluation, machine learning workflow, and application performance monitoring in general. It has been shown that current disjointed solutions fail to protect unbound state space agentic architecture from serious threats such as alignment drift, SaaS security concerns, and unauthorized deployment of shadow AI systems. Moreover, a solution is proposed for overcoming the discussed challenges in form of a coherent multi-level AI governance stack Traccia built on the top of OpenTelemetry infrastructure platform. Traccia resolves the last mile for AI Alignment by adding the telemetry data, passive semantic guardrail assessment, and execution lineage into a hashed trace ledger. Traccia automatically creates compliance evidence packages by appending tamper-resistant fingerprints and SHA-256 content hash, that map to regulatory requirements (Articles 12, 14, 19, 26(6), and 50 of the EU AI Act) without invading any data privacy. By performing this evaluation in a methodical manner, a solid machine-readable base has been created for enterprise-wide management of autonomous AI systems.

Multi-reference-to-audio-video (MR2AV) generation aims to generate coherent audio-video content conditioned on multiple references and textual instructions. Existing benchmarks mainly focus on text-driven generation, single-reference subject preservation, or isolated audio-video alignment, leaving the emerging MR2AV setting largely unexplored. Compared with these settings, MR2AV requires models to jointly reason over multiple references while generating synchronized visual and audio content. Models must not only preserve each reference faithfully but also correctly bind and compose multiple referenced entities into coherent audio-visual events. To address this gap, we introduce MultiRef-Compass, a unified benchmark for MR2AV generation. It comprises $350$ carefully curated samples constructed through a scalable and controllable asset-composition pipeline, covering multi-view subject preservation, multi-entity binding, and human-object-scene composition. To provide interpretable assessment, MultiRef-Compass defines an evaluation protocol with four dimensions: Basic Quality, Reference Consistency, Audio-Visual Consistency, and Instruction Following, using 14 sub-metrics. MultiRef-Compass integrates automatic metrics with a rejudging-enhanced MLLM-as-a-Judge framework, enabling scalable and auditable evaluation of both perceptual fidelity and reference-conditioned composition. Extensive experiments on eight representative MR2AV systems reveal substantial room for improvement across multiple evaluation dimensions, underscoring the need for a comprehensive benchmark and positioning MultiRef-Compass as a foundation for future MR2AV research.

Large language models are increasingly deployed in agricultural decision-support settings, yet high-stakes crop protection in smallholder agriculture requires more than output-quality benchmarks. Over a two-year design and evaluation programme, we formalise policy-constrained large language model assessment as an adaptive compute allocation problem that jointly captures safety compliance, helpfulness, operational latency, and expert supervision workload. We introduce P-EVAL (Policy-grounded Expert-calibrated VALidation protocol), a unified evaluation framework for policy-grounded decision support, evaluating the architecture on a simulated field query database consisting of 1,240 cases. The protocol is instantiated on the Pezego advisory architecture (Pezego-HITL) and evaluated in Ghana. Following offline judge calibration against gold-standard human expert decisions ($κ= 0.77$), we evaluate the architectural performance under simulated query workloads. Under P-EVAL, our memory-routed architecture improves the Policy Alignment Rate (PAR) to 0.94 and the Agronomic Utility Rate (AUR) to 0.95, while reducing P95 latency by 55% (from 28.6s to 12.9s) through a 59.6% cache reuse ratio. We also demonstrate generalisability using the open-source \texttt{Qwen3.5-9B-DeepSeek-V4-Flash} model, achieving a PAR of 0.86 and a 54.5% latency reduction (to 10.2s). To evaluate practical utility and socio-technical integration, we administer detailed questionnaires to Ghanaian Extension Services Officers ($N=30$) and smallholder farmers ($N=36$). Taken together, this work demonstrates how policy-grounded structured retrieval-augmented generation with validated-memory routing makes safety-utility-latency trade-offs explicit, offering a scalable template for trustworthy AI-driven extension in smallholder farming systems.

Studies of bias in LLM-as-judge systems typically build synthetic corpora by prompting an LLM to generate a hallucinated answer to pair with a factual one, then presenting both to a judge. We report a case in which this generation step silently failed, and use it to argue that the failure mode is structural rather than incidental. In a multilingual (Turkish/English) faithfulness-judgment corpus, a decoding-budget parameter shared between judging and generation calls truncated one producer's hallucinated answers to a few words. The resulting items produced a large, statistically robust effect: a 32-point cross-lingual collapse in one judge's selection accuracy, replicated from N=50 to N=500, explained by a three-layer mechanistic account, and confirmed by a controlled producer-swap experiment, none of which was real. The effect vanished to ceiling once the shared parameter was corrected, and only manual reading of the raw generations, not any aggregate statistical check, exposed the fault. A second measured bias (Markdown-formatting preference) was not fabricated but distorted by the same fault, its magnitude and in one case its sign shifting with stimulus length, a mode aggregate metrics cannot distinguish from the first. We frame the underlying vulnerability using the test oracle problem: corpora whose negative examples are LLM-generated carry no mechanical way to verify item integrity, while corpora built by deterministic perturbation of a gold answer carry an item-level oracle for free. A positive control supports this claim directly: an analogous fault injected into a minimal perturbation-based corpus is caught with 100% accuracy by a zero-cost, zero-human gold-to-negative string comparison. We close with a validation protocol, derived from our own case, for analysts working in the oracle-less regime that we argue describes most contemporary multilingual LLM-as-judge corpora.

Large audio-language models (LALMs) are increasingly used as automatic judges for speech evaluation. However, high agreement with human ratings does not guarantee that their verdicts are grounded in the audio. A judge may instead rely on specialist labels or reference data supplied by the evaluation protocol itself, taking a shortcut in place of listening to the audio. In this paper, we audit such protocol-level ``shortcuts'' in LALM judges across three common deployment protocols: feature-blueprint judging, where the audio is replaced by a structured text description of acoustic features, reference-conditioned judging, and pairwise A/B comparison. Across six judges and four attributes, we find that several LALMs rely on protocol-level shortcuts. For example, in feature-blueprint judging, incorrect specialist labels reduce five judges' emotion accuracy to 0.10 or below, and in concatenated A/B comparisons, Qwen3-Omni-Thinking often picks the same slot regardless of order swaps. These results indicate that aggregate agreement can overstate the validity of LALM judges unless the model and the evaluation protocol are assessed jointly, and that each model-protocol pair should be evaluated with a matched shortcut probe.

LLM-as-a-judge is widely used to provide feedback and selection signals in closedloop regeneration, but this use remains insufficiently validated. We study it in table recognition, where deterministic TEDS evaluation provides a controlled testbed, using FinTabNet and OmniDocBench. Three findings emerge. First, judge signals were weak on both datasets: scores frequently tied, rankings were not reproducible, and the only selection policy that beat random on both datasets depended on an earliest-iteration tie rule, so its advantage cannot be attributed to the judge scores alone. Iteration produced better candidates, but the judge failed to recover them. Second, severe losses occurred even without specific judge feedback. A structurepreserving instruction significantly reduced the severe-loss rate on FinTabNet and was directionally consistent on OmniDocBench. The contrasts support target-preservation failure under unconstrained regeneration as a proximate mechanism of the observed severe losses. Third, the structure-preservation constraint reduced the severe-loss tail but produced no improvement. In an exploratory 2x2 analysis, the same protection was not stably observed when judge feedback was retained. These results do not dispute the value of LLMs as evaluators. Instead, they show that evaluation ability does not imply optimization utility. Iterative refinement requires, at minimum, a verification signal that deterministically detects structural change, rather than judge scores alone.

The evaluation of mathematical reasoning in large language models (LLMs) has predominantly focused on high-resource languages like English. This has created a significant barrier to the equitable development and deployment of AI in linguistically diverse regions such as Bangladesh, where over 230 million people speak Bengali. Despite this global significance, there has been minimal prior work on mathematical reasoning in Bengali and no existing research that systematically benchmarks a perturbated Bengali mathematical dataset, leaving a critical void in assessing model robustness and true comprehension beyond pattern recognition. This study addresses this gap by introducing GSM-Plus-BN, a novel perturbated Bengali mathematical dataset derived from the English GSM-Plus benchmark and verified by human translators. We evaluate six open-source LLMs Qwen3-32B, Llama-3.1-8B-Instant, Llama-3.3-70B-Versatile, Llama-4-Scout-17B-16E-Instruct, GPT-OSS-120B, and GPT-OSS-20B using a benchmark of 9,000 evaluation samples comprising 1,000 seed questions and 8,000 perturbed variants under both Standard Prompting and Chain-of-Thought (CoT) Prompting. Experimental results show that GPT-OSS-20B achieves the highest seed question accuracy of 96.08% under Standard Prompting, while larger models such as Llama-3.3-70B and GPT-OSS-120B demonstrate superior robustness across perturbation types. Furthermore, CoT prompting substantially improves reasoning for most models compared to Standard Prompting, yet a notable performance gap persists across all models relative to their English benchmarks, underscoring the inherent difficulty of perturbed Bengali text. This research makes a foundational contribution by providing GSM-PLUS-BN as a new resource and baseline for future Bengali mathematical reasoning research.

LLMs now sit on every side of evaluation: as examinees scored on benchmarks, judges of other models' outputs, and raters of human-generated content. Each paradigm can be viewed as a measurement problem, where a latent property of an object is probed with items from an instrument (e.g., benchmark) by judges or raters. Standard evaluation practices often neglect the contributions of each core component to the end result, limiting our understanding of what is being measured. Rasch measurement theory (RMT) is well-suited to this problem. RMT decomposes ordinal ratings into separable facets on a common scale. It further provides a battery of diagnostics that can identify miscalibrated measurements and rater biases. We present a case study of RMT applied to the LLM-as-rater paradigm using the Measuring Hate Speech corpus, whose construct was itself built under RMT. We fit a series of many-facet Rasch models to annotations from nine LLMs spanning families and capability levels. Our analyses show that LLMs systematically differ from human raters in severity, item-level calibration, question-order robustness, target-identity sensitivity, and rating scale use, all of which standard evaluation practice would largely obscure. Overall, we argue that RMT belongs in the toolkit for evaluating LLM-as-examinee, -judge, and -rater paradigms.

LLM judges are increasingly being used to evaluate open-ended model responses, often in no-reference settings where a ground-truth answer is unavailable. However, can they reliably assess in such evaluation setups? We explore this question in this paper through a two stage pipeline with a) calibration experiments that assess the judge model's knowledge of the task it is evaluating, and b) sensitivity experiments that assess how the judge model's performance is impacted by the presence and positioning of the reference answer in the prompt. Across experiments covering three languages, we show that the judge models we evaluated tend to over-credit incorrect answers in the absence of a reference answer, and adding reference answer information to the prompt flips the judge model's correct/incorrect decisions by as much as 85% in some experimental settings. Comparison with a subset of human annotations shows that these reference-driven changes generally align with human judgments. Our results emphasize the need for calibrating the LLM judges with a sample with reference-aware evaluation before using them in reference-free setups reliably, and our methodology provides a blueprint for researchers and practitioners in doing such calibration of LLM judges for other tasks.

Existing studies of LLM-as-judge scoring bias work predominantly at the input-output level: they perturb inputs, measure score deltas, and propose prompt-level mitigations. We argue that the same biases admit a representation-level account in the judge's hidden state, complementary to the input-output view and operationally useful in ways it does not afford. We report three findings, across seven judges, seven bias types, and nine benchmarks. Geometry: baseline judging inputs occupy a tight activation manifold while biased inputs are displaced along a low-dimensional, type-specific subspace that sharpens with depth and is recovered consistently by three families of estimators. Causal control: steering hidden states along this subspace drives scoring in both directions, forward shifts reproducing biased scoring on clean inputs and reverse shifts restoring baseline scoring on biased ones, while matched-norm random directions produce shifts an order of magnitude smaller. Operational: a simple linear projection onto the same bias-direction features anticipates judge failures on three entirely unseen benchmarks, substantially outperforming text-based alternatives. Reading bias as activation geometry, rather than as input-output noise, unifies geometric structure, causal control, and operational prediction within a single framework. The project page is available at https://xzx34.github.io/unfair-judge/

In the rapidly evolving landscape of information retrieval systems, the ability to adapt and improve through user feedback is paramount. This study introduces a novel methodology for refining the performance of a primary Retrieval Augmented Generation (RAG) system by strategically integrating an auxiliary feedback RAG system. By systematically harnessing human-generated feedback, the approach aims to enhance the accuracy, relevance, and overall quality of responses, driving the system towards self-improvement. Central to this methodology is a human-in-the-loop implementation, where user feedback is continuously collected, classified, and integrated into the inference workflow, enabling the system to learn and evolve iteratively. To validate the effectiveness of this approach, the study employs rigorous testing against three diverse benchmark datasets focused on general and custom domain knowledge, utilizing a LLM-as-a-Judge evaluation strategy. This comprehensive framework not only underscores the transformative potential of feedback-driven enhancements in RAG systems but also sets a precedent for future research in adaptive information retrieval technologies, marking a significant step in the journey towards autonomous refinement and optimization through user engagement.

Existing benchmarks for scientific data analysis evaluate LLMs primarily on code execution or workflow completion, overlooking that scientific analysis serves to support distinct types of scientific claims: hypothesis exploration, statistical inference, mechanistic explanation, each with different assumptions and validity criteria. We introduce SDABench, a benchmark that reorganizes evaluation around six capabilities (descriptive, exploratory, inferential, predictive, causal, and mechanistic) across five domains (Biology, Chemistry, Environment, Geography, Physics). SDABench comprises 527 real-data instances (SDA-Real) and 6000 synthetic instances (SDA-Synth), each in both multiple-choice and open-ended formats, constructed through an automated pipeline. Evaluating 15 representative LLMs, we find that models handle descriptive analysis well but degrade sharply on tasks requiring assumption selection, latent-process modeling, or mechanistic reasoning. SDABench further provides a five-stage error analysis framework that locates where LLMs fail: more advanced models more reliably identify the relevant scope and variables, but still struggle to select appropriate analytical procedures, model variable relationships, and draw valid conclusions.

Contemplative traditions have long guided ethical behavior and prosocial interaction, and recent work suggests that contemplative principles (e.g., mindfulness, compassion, non-dual reasoning) may offer a promising paradigm for aligning large language models (LLMs), improving cooperation and reducing ethical violations in LLM outputs. However, as new models, evaluation metrics, and benchmarks emerge rapidly, it remains challenging to systematically assess whether and how contemplative principles enhance LLM alignment across diverse and evolving scenarios, and existing approaches are often ad hoc and fail to generalize. We present a modular, extensible evaluation framework, initially targeted at the mental health domain, that enables seamless integration of new models, metrics, and benchmarks through a reusable pipeline. The framework currently reproduces existing state-of-the-art results and supports systematic cross-evaluation by flexibly mixing and matching models, metrics, and benchmarks, enabling fair comparison and deeper insight. Its plug-and-play prompting module offers a principled pathway for incorporating ethical perspectives such as contemplative principles, allowing domain experts to define alignment criteria without requiring technical expertise. Although initially focused on mental health, the framework is domain-agnostic and extends naturally to areas such as decision-making, moral reasoning, and human-AI collaboration. By bridging computational evaluation with human-centered ethical reasoning, this work lays the groundwork for interdisciplinary research spanning cognitive science, behavioral economics, philosophy, and system design, toward robust, trustworthy, and socially beneficial human-AI ecosystems.

LLM-as-a-judge evaluation is widely used for retrieval-augmented generation (RAG), but reusing the same model family as both generator and judge makes self-leniency difficult to identify. We introduce Eval-Pair Matrix, a controlled meta evaluation protocol for source-grounded RAG. Starting from GaRAGe questions and grounding passages, we induce one hidden answer-causal contradiction per record, generate answers from perturbed passages with GPT, Grok, and Gemini models, and then use the same models as blind judges to evaluate each answer against the original passages. The experiment contains 300 core records, 897 labeled generator outputs, and 2,683 judge verdicts in a crossed 3 x 3 matrix; the primary analysis uses 275 fully validated records. Instead of comparing diagonal and off-diagonal cells across different answers, we estimate same-model effects by pairing judges on the exact same candidate answer. This changes the interpretation: diagonal and off diagonal F1 are similar, and the paired same-model recall effect is near zero (-0.5 pp; 95% cluster bootstrap CI [-2.7, +1.7]). The only robust paired gap is lower matching-judge flagging for answers that avoided the induced claim (-4.3 pp). A targeted human evaluation finds that reviewed apparent false positives are alternate source-error detections, mistakes in labeling whether the induced claim was adopted, or unclear cases; none were adjudicated as genuine false alarms. The lesson is methodological: RAG judge studies should report full matrices, answer-paired effects, behavior strata, and label-task alignment.

When an LLM judge calls a peer review analytical and a human committee calls another review high quality, are they tracking the same thing? We argue they are not, and that the difference matters philosophically. We operationalise Kahneman's dual-process theory into a structured rubric for peer review and release Kahneman4Review, a benchmark of 3,563 rated reviews scored along nine theoretically motivated textual dimensions, eight bias diagnostics, and a continuous reasoning-quality score. Three findings bear on trustworthiness: decision tier is not detectably aligned with the rubric's text-grounded epistemic-quality proxy; public-showcase agentic reviews receive higher raw scores than pooled human reviews, but length and venue explain most of the gap and the samples are not paper-paired; and ICLR review-text diagnostics shift at the 2022--2023 transition, temporally coincident with widespread LLM availability but without identifying its cause. A matched function-probe pilot further shows that the rubric distinguishes textual probes designed to contrast genuine fault-finding with surface fluency. We argue that a trustworthy reliability benchmark for LLM judges must separate analytical form from epistemic function, and propose concrete design choices toward that goal. An interactive demo is available at https://huggingface.co/spaces/nuojohnchen/Kahneman4Review.

Short-answer VQA benchmarks conflate two distinct quantities: whether a model's answer is semantically correct, and whether that answer matches the surface form expected by the automatic evaluator. We study this conflation across six vision--language models and six benchmarks, using a human-validated semantic judge (97.6% precision) to audit over 37k official errors. A second text-only judge reproduces the same benchmark-level false-negative pattern, showing that the effect is not an artifact of a single audit model. On text-rich benchmarks, up to half of these errors are semantically acceptable answers penalized purely for surface-form mismatch. This instability is structured by answer type: extractive and multi-span answers are far more evaluator-sensitive than scalar answers. Benign prompt and context rewrites further destabilize official outcomes, flipping item-level correctness at substantial rates without changing the underlying task. A deterministic CPU-only contract repair confirms that the undercount is partially recoverable. These findings imply that official short-answer VQA scores should be accompanied by semantic audits and answer-type diagnostics to remain interpretable.

Previous work in group recommender systems has demonstrated a sensitivity to the distribution of preferences within a group. Specifically, the selection of the preference aggregation strategy benefits from considering such group configurations. In this paper, we study whether LLMs are able to mimic this sensitivity and to select the ideal aggregation strategy (and corresponding recommendation) according to nuanced human perceptions of fairness, satisfaction, and consensus. We do this by fine-tuning Large Language Models (LLMs) on human survey data to serve as real-time judgmental models within the recommendation pipeline. Using a reasoning dataset distilled from DeepSeek-V3.1 and human ground truth assessments, we develop Judgmental Llama and Judgmental OLMo to simulate group assessments. Our pipeline successfully generates multiple recommendation candidates based on social choice-based aggregation strategies and dynamically selects the one that maximizes these predicted human-like evaluations. We further validate these suggestions in a user study (n=284) and find that our methodology achieved the highest scores for satisfaction and group consensus. Furthermore, we find that LLM judgments are most aligned with human perceptions of fairness, satisfaction and consensus when we also consider interaction effects between our LLM-based method and group configuration (e.g., minority or coalition). These findings give further support for dynamically adapting aggregation strategies to specific within-group preference distributions, and highlight the advantage of using LLMs for an adaptation that is aligned with subjective human judgments.

Selecting the correct answer from a pool of candidate reasoning chains is the engine of test-time scaling, yet the standard selectors each carry a cost: self-consistency inherits the errors of the single model it resamples, and trained reward models need labeled data and transfer poorly off-distribution. We study a third signal, free at inference time: cross-model consensus, the degree to which independently trained models, each solving the problem once, agree on a final answer. We treat the panel as an LLM-jury, in which the structure of agreement, not any model's score of another, is the verification signal. Across seven benchmarks it selects correct answers better than self-consistency and far better than a model scoring its own candidates: on competition math it closes the entire gap to an oracle selector, while self-scoring closes almost none. The mechanism is error decorrelation: independently trained models err differently, so their wrong answers scatter while the correct one accumulates agreement. We make this precise with a parameter-free law, derived in closed form, that predicts consensus accuracy from three measured panel statistics to a mean absolute error of $0.03$ and exposes the method's ceiling: a shared-error floor where models share a misconception, near zero on math but non-trivial on science. Against four trained verifiers spanning discriminative, outcome, and generative reward models, the free LLM-jury matches the strongest inside their math training domain and is the top selector outside it. Cross-model consensus is thus a verifier we can characterize in advance: a law that says when to trust it, and a floor that marks where it cannot.

Reinforcement learning increasingly relies on an LLM judge to score each rubric criterion, and that judge acts as the reward model during training. Before such a signal can be trusted, we need to know how capable the judge must be and how biased it is. We study this calibration question for citation quality in deep-research systems, where a search-grounded LLM must support each claim it writes with a cited source. Citation quality is a structured rubric task in which each attribution-citation pair is judged along two dimensions that require an LLM, source relevance and factual support. On an adversarial long-form benchmark, we score 8 off-the-shelf LLM judges from 3 model families against gold labels over 1,248 rubric decisions, all of which were human-reviewed and 378 of which were hard cases adjudicated from judge disagreements. Cheaper judges remain competitive across both dimensions, with GPT-5-mini attaining the strongest source-relevance pass-class F1 at 0.908 ($κ$=0.636), while on factual support the judges are statistically indistinguishable (overlapping confidence intervals), so no single model dominates. At comparable F1, the judges still differ substantially in pass-rate drift, false positive rate, and false negative rate. Scalar F1 obscures this directional bias, yet it is exactly what a downstream reinforcement learning loop would reinforce. Calibrating the judge is therefore a prerequisite for using citation rubrics as reward signals, and our results show that this calibration does not require the most expensive available model.

An LLM-as-judge score can move even when the candidate responses stay fixed, simply because the evaluator has changed. We treat this evaluator-replacement ambiguity as a measurement-validity problem. Across four judgment datasets, we compare two upgrade paths available in practice: scaling Qwen3 dense judges from 1.7B to 32B parameters and moving across MiniMax M2-M2.7 released APIs. The main pattern is that judge upgrades are not interchangeable: only Qwen3 1.7B to 4B gives a robust adjacent gain, while MiniMax adjacent releases do not. Stronger judges reduce but do not remove position and verbosity bias. Repeated-sample juries add little when errors are correlated. Structured debate can move decisions substantially, but without parser and fallback logs those shifts cannot be attributed to deliberation. We argue that LLM-as-judge reports should include dataset slices, bias probes, error-dependence estimates, and protocol audit trails.

Personality recognition has traditionally been constrained by theory-dependent formulations, where models are trained to fit predefined psychological taxonomies rather than uncovering shared underlying behavioral structure. This limits generalization, as personality itself is better understood as theory-invariant, while existing annotations reflect only partial and sometimes inconsistent views of the same latent traits. In this work, we introduce JAM ((J)udge for (A)daptive (M)etric-Alignment), a theory-agnostic framework that shifts learning from adapting to predefined personality theories toward discovering unified latent pseudo-facets that capture shared psychological structure. Rather than constraining the model to any personality taxonomy during training or inference, the framework learns generalizable psychological representations and can infer an individual's latent psychological profile directly from the textual samples, without requiring theory-specific labels. JAM achieves this through an Attention-Pooled Graph Prototypical Network that learns structured representations via clustering in embedding space, together with a Cross-Theory Harmonization (CTH) approach that integrates (i) Human-Guided Linkage and (ii) Machine-Induced Consensus to unify heterogeneous datasets without relying on predefined labels. To further improve robustness and data quality, we incorporate an LLM-as-a-Judge mechanism operating in two configurations, (i) LLM-before-the-loop and (ii) LLM-in-the-loop which identifies ambiguous samples to guide adaptive metric learning. Experiments show that JAM improves cross-framework generalization and performance, establishing a strong step toward theory-agnostic personality inference and supporting low-resource personality theories. The related code repository, model weights, and artifacts are available at https://research.jingjietan.com/JAM

Large language models (LLMs) have demonstrated rapidly improving long-context capabilities, prompting a wave of benchmarks designed to evaluate them. However, existing long-context evaluations - from Needle-in-a-Haystack (NIAH) tests to more recent multi-hop reasoning and summarization tasks - predominantly measure average-case performance, and many are either saturated or lack robustness. Notably absent is a systematic way to probe how models perform as we scale up the difficulty of tasks along various axes. We address this gap by proposing PredicateLongBench, a benchmark that stress-tests long-context reasoning by asking models to identify the longest contiguous subsequence of words in a long input that satisfies given predicates/constraints (e.g., lexicographic ordering), drawn from a broader predicate class. The central innovation of our benchmark is the identification and systematic exploration of multiple different axes of difficulty which test multiple aspects of long context understanding. We provide two complementary generation pipelines - a fully synthetic setup using random word-like strings, and a real-world setup that samples words from natural documents while preserving their distributional properties. We find that frontier models struggle to perform well as we scale up the difficulty of tasks along our axes, demonstrating the utility of our benchmark in understanding the limitations of current long-context capabilities. Furthermore, the tasks in PredicateLongBench, though challenging, are conceptually simple and do not require LLM-based generations or judges.

LLM-as-judge (Zheng et al., 2023) is increasingly the default for evaluating AI systems in enterprise pipelines, often scaled to ensembles (Verga et al., 2024) or "mixture-of-experts" (Shazeer et al., 2017) panels of judges. These systems share a key assumption: that consistency -- agreement among judges, or among a model's own samples -- indicates correctness. We show this assumption is unreliable. Agreement is not accuracy: a model can agree with itself, and different models can agree with each other, out of shared bias, a memorized heuristic, or an option-position prior rather than truth. We ask when agreement is nonetheless a usable proxy, in a large-scale cross-runner study: 53 runners drew K=50 samples for assigned overlapping cases across comparisons of model tier, prompting, and scale on GPQA Diamond and AIME -- 265,000 samples. Using majority-correctness as the deployment label and a hierarchical runner-clustered bootstrap, agreement is a positive but weak predictor (rho 0.20-0.59, all positive under item-clustered resampling) whose usefulness is regime-dependent: best for unsaturated mid-tier models and for allocating compute, and worst -- over-confident yet no more accurate -- for the most consistent frontier model (agreement >=0.8 on 77% of GPQA case-result entries, 48% of those wrong). An exploratory cross-family check on three Claude tiers shows the same frontier over-confidence, with confident errors recurring across providers above a marginal-preserving null. Self-consistency is thus a conditional proxy for correctness, not a standalone confidence score. We publicly release the de-identified per-run rows and answer distributions.

A self-evolving agent retires its bad skills by watching them fail, so what happens when the judge cannot see the failures? Skill retirement is the structural constraint that keeps a growing library from drifting below the no-skill baseline, but its guarantee assumes an unbiased reward, which is false for the LLM judges that reference-free tasks force upon us. We show that a biased judge does not merely add noise; it \emph{silently switches off the curator}. We make this precise with a corrupted-reward analysis and, isolating the causal channel by injecting corruption on top of a deterministic reward, a behavioral study on a reference-free report-writing testbed with a code-generation cross-check. Symmetric noise leaves retirement intact, but \emph{false-pass} bias (failures slipping through as passes) disables contribution-based retirement past a sharp threshold that no amount of data can cross. Separating genuine retirement from cap-eviction churn shows this \emph{mechanism} failure is universal, holding across domains and failure rates and sparing only near-zero-false-pass, verifier-like graders. The downstream \emph{outcome}, though, is regime-dependent: eval quality degrades only where the same corruption also starves skill synthesis, and otherwise holds steady, so the disabled curator is \emph{silent}, surfacing in no aggregate metric. The contribution is a behavioral safety result, not a performance one. A cheap defect-injection audit then tells an operator, before deployment, which side of the threshold their judge occupies.

Pre-deployment safety evaluations aim to inform the downstream risks of releasing a new AI model. Yet most evaluations provide limited evidence about how often undesired model behavior will occur in deployment: they generally have insufficient coverage, are unrepresentative, and are generally recognizable as tests. To address these concerns, we study a simple way to simulate a model deployment: starting from de-identified conversations from a previous model deployment, we hold fixed the initial conversation prefix and regenerate the next response using a candidate model. The resulting responses can then both be audited for novel misalignments and used to estimate the prevalence of model misbehavior before deployment. We evaluate deployment simulation across four GPT-5-series deployments, using registered, outcome-blinded predictions for GPT-5.4 and retrospective analyses of three earlier releases. We find that deployment simulation produces informative estimates of post-deployment misbehavior rates and outperforms baselines based on adversarially selected production data; its evaluation-awareness point estimates were also much closer to production traffic than those from traditional evaluations. We also identify the realism of tool resampling as a central challenge for further improving predictions and share results suggesting that this challenge is surmountable even in complex tool-use settings. Finally, we show that deployment simulation can be seeded from public chat datasets and remain informative about production misbehavior rates, suggesting a path for external researchers to run deployment-grounded evaluations without access to private production logs. Overall, deployment simulation helps evaluators forecast how language models will behave in the real world and supports more quantitative assessment of deployment risk.

The remarkable performance of large language models (LLMs) in linguistic tasks underscores an urgent need for comprehensive evaluation of their response quality. Prevailing methods, often confined to singular dimensions, fall short of capturing the full spectrum of model capabilities. This study introduces a multifactor scoring paradigm, integrating accuracy, conciseness, factual consistency, readability, and coherence, complemented by a graphical user interface (GUI) for visualizing outcomes. Evaluations on the TruthfulQA dataset unveil mainstream LLMs' strengths in reasoning tasks (peaking at a composite score of 0.6104) alongside pervasive limitations in navigating complex facts and ambiguities. Transcending the narrow lens of traditional metrics, this framework offers a transparent, adaptable avenue to illuminate model potential and deficiencies. Though presently focused on English tasks, its horizons beckon toward multilingual domains. This work carves a novel path for knowledge engineering and model refinement.

Large language models (LLMs) are increasingly applied to reverse-engineering tasks, and recent threat-intelligence reporting shows them operating inside live offensive-security workflows. Claims about their capability, however, outpace our ability to measure it. Existing benchmarks for LLM-assisted binary analysis treat the construction of function-level ground truth as a solved pre-processing step and report accuracy without disclosing how many functions were reliably evaluable. We argue that the principal obstacle to fair evaluation is not model capability but the reliability of binary-to-source alignment under compiler optimization. This paper presents Reforge, a provenance-tracked pipeline that constructs function-level ground truth from C source through compilation, DWARF and syntactic extraction, alignment, and decompilation, and that operationalizes alignment uncertainty as an eight-gate confidence funnel with three-tier stratification. On a controlled micro-benchmark, high-confidence yield falls from 87.2% to 65.9% across optimization levels, and unpaired comparisons overstate optimization-induced performance decay through survivorship bias. A proof-of-concept evaluation of seven contemporary LLMs on function naming demonstrates the substrate and motivates uncertainty-aware benchmarking practice

Evaluating uncertainty in AI-generated SQL queries requires estimating whether a query is correct, where correct means it executes to the same result as a human-written reference. We study which signals predict correctness on hard multi-table text-to-SQL, using AUROC to measure how well each ranks correct queries above incorrect ones. On BIRD and Spider, black-box signals such as string, structural, and execution self-consistency, a schema-relevance score, and query executability all fall between about 0.61 and 0.68 AUROC, with string self-consistency strongest at 0.675; white-box log-probability is similar (0.67). The signals that move past this ceiling are verification-based: an LLM judge scores from 0.72 (GPT-4o-mini) to 0.78 (Claude). Judges from different providers make different errors, so a two-provider ensemble reaches 0.82 AUROC with a well-calibrated probability (expected calibration error 0.03) and supports useful abstention frontiers (for example, answering 27% of questions at 24% selective risk) where self-consistency offers no valid low-risk subset. The pattern holds across two benchmarks, two generators, and two judge providers. We also ask whether a verifier can be trained. Fine-tuned verifiers, both encoder and generative, reach about 0.77 to 0.79 AUROC in-distribution but fall to about 0.66 on unseen schemas; scaling to 7B, adding schema diversity, distilling a strong judge's rationales, and cross-benchmark training all fail to close that gap. Cross-schema transfer appears to track model scale and reasoning rather than fine-tuning. In practice, correctness uncertainty for text-to-SQL lives in reasoning-based signals: a fine-tuned verifier is a good in-domain tool, but a verifier that generalizes across schemas currently means a large frozen reasoning model.

Current benchmarks for evaluating Large Language Models (LLMs) in data analysis often fail to reflect real-world settings. They typically focus on fact retrieval from small tables and overlook the challenges of large multi-tabular datasets, external knowledge integration, and exploratory insight discovery. We introduce DataGovBench, a benchmark derived from governmental open data designed to evaluate LLMs in practical scenarios. The benchmark includes two tasks: Table QA that requires solving complex decomposable questions and producing textual answers or visualizations, and Table Insight that evaluates the ability of models to generate expert-level findings through exploratory data analysis. Comprehensive experiments with state-of-the-art LLMs, both with and without agentic frameworks, reveal significant performance gaps across both tasks. These results suggest that current LLM-based systems remain far from satisfying the demands of real-world data analytics. DataGovBench provides a challenging benchmark for advancing research on LLMs capable of both answering analytical queries and discovering insights from data. Code and sample data are available at https://github.com/SoHasegawa/datagovbench.

Audio Descriptions (ADs) narrate visual content for Blind and Low Vision (BLV) audiences during gaps in audiovisual media. There is growing momentum around ADs in movies and TV shows, and with mandates from India's Central Board of Film Certification (CBFC), there is a need to expand ADs beyond English. Yet, there is no work that generates ADs for any Indian language. To address this gap, we present the first systematic study of ADs in Hindi, contributing to aspects such as data, generation, and evaluation. We introduce Andha-Dhun, the first dataset of human-authored Hindi ADs collected from 8 full-length movies. We explore two approaches for generating ADs in Hindi: (i) directly from English dense video descriptions, and (ii) translating English ADs into Hindi. We evaluate these approaches using perplexity and LLM-as-a-judge metrics to assess fluency and quality respectively. We also analyze movies that have both English and Hindi human-authored ADs and find that naive translation introduces artifacts and narrows diversity compared to original Hindi ADs. Direct machine translation fails to adapt cultural references, while human-translated ADs do better but still fall short. Our findings emphasize that the purpose of Hindi ADs is accessibility for Indian BLV audiences, and that this requires adapting content for the audience more than strict fidelity to the source.

Training a language model against its own reference-free judgments (the premise of self-rewarding, self-play, and LLM-as-a-judge pipelines) assumes a model's verdict on a shown answer tracks correctness. We show it fails structurally: conditioned on a candidate, a judge scores plausibility, not correctness, leaving false-positive basins a policy learns to exploit. We measure this with a hidden-anchor audit: a held-out, cross-source exact-match check the judge never sees. On GSM8K with Qwen3 policies, self-play drives the judge's pass rate from 0.72 to 0.94 while true accuracy stays at 0.20 (three seeds). This reward hacking is not white-box gaming: the errors transfer across judge families (Qwen, Llama, Gemma) and scales, a strict three-judge ensemble still accepts 55% of them, and no plausibility-scoring defense closes the basin. The decisive variable is whether the judge commits an answer of its own before using the candidate: committing first drops the false-positive rate from 0.719 to 0.012, blind solving lifts discrimination to 0.96, and used as the training reward the de-anchored channel keeps false positives at zero, preventing the basin rather than only detecting it. A falsifiable bound (the gap is at most 1 - accuracy) predicts which regimes are exposed. The full arc replicates without training under best-of-N selection in code and competition math, and with a Gemma policy.

Imagine two users interact with the same LLM. One has been told it is the cutting-edge flagship model; the other, an older, weaker model. They walk away with markedly different ratings of its usefulness and intelligence, yet they used the same model. In a controlled study, 162 participants each used one of six LLMs from two families across three collaborative tasks, after first viewing a landing page that matched, overstated, or understated their model's true capability. This pre-interaction framing shifted user opinions and interaction behavior while task performance did not. Oversold users rated the model more favorably and used more directive prompting, while Undersold users wrote longer, more collaborative prompts. The quality of what users and the model produced together depended only on the model's true capability, not on what users were told. Participants' change in model impressions after use, measured across two impression measures, was not predicted by task performance ($β= -0.01$ and $0.11$, both n.s.), but by whether the model met users' expectations ($β= 0.47$ and $0.50$, both $p < .001$) and how confident they felt working with it ($β= 0.47$ and $0.36$, both $p < .001$). After interaction, users are still rating the pitch, not the product: user-elicited LLM evaluations, including the preference data driving public leaderboards, measure expectation management at least as much as the model itself.

This article is about the development of a fuzzy cognitive map using a local large language model. In the light of recent advances it is evident that large language models, and even local large language models are capable of extracting quantities from textual data. In other words, a local LLM like Qwen2.5-32B, or probably larger, can accept entities as prompt input and determine relevant quantitative data as the model output. In turn, this output can be utilized for the construction of a data driven fuzzy cognitive map. Hence, this implementation is achieved and then the model is thoroughly tested; Qwen2.5-32B is used and the data is extracted from hotel reviews from TripAdvisor. Furthermore, the extracted documents pass through the model unfiltered and then a fuzzy cognitive map is trained and evaluated. A case is made about Greek reviews where a star topology FCM is formed that indicates the preferences of the reviewers. Finally, external validation is performed to establish whether the fuzzy cognitive map can correlate the star rating of the review -an outcome outside the model's inference scope -with its predicted satisfaction.

When evaluator-derived step rewards are pooled or compared across scoring channels, their sign is treated as transportable. Yet the same frozen transition can change sign with the scoring channel. Process rewards vary agent states, while evaluator audits vary scoring configurations; neither first difference isolates their interaction. We define Agent Step Value (ASV) as channel-indexed target-margin gain and identify the missing state-by-channel interaction by replaying complete faces. Of 1,100 PubMed open question-answering transitions, 1,004 were complete across four cyclic layouts. Their mean update is positive under direct scoring (+0.163 [0.102, 0.218]) and negative with an externally generated view (-0.160 [-0.244, -0.079]), giving an interaction of -0.323 [-0.418, -0.232]. Across paired transitions, 507/1,004 cross zero in one direction or the other. Matched templates isolate a generated-minus-quote interaction of -1.121 [-1.534, -0.703]. Its direction remains negative after the readout and evaluator-stack changes, and quote yields a higher paired area under the receiver operating characteristic curve (AUC) for stored success at all three bridge vertices. Because the two views preserve the same task information conditional on the retained state, a representation-invariance null predicts equal responses and success rankings across them. ASV provides a transport audit for evaluator-derived step measurements; causal actor credit lies outside its estimand.

The rapidly growing repository of publicly available large language models (LLMs) presents significant challenges for systematic management and quantification at scale, such as model lineage tracing, licensing, and evaluation. However, task-specific benchmarks are insufficient for this setting, as LLMs differ widely in architectures, scales, and training procedures. To address this challenge, we adopt spectral shape-based metrics for managing and quantifying LLMs based on Heavy-Tailed Self-Regularization theory. Our approach uses the shape information of the weight empirical spectral density as a compact spectral signature of each model. This signature captures intrinsic properties of pretrained models and remains robust during post-training, making it suitable for model-level analysis. In addition, this metric is data-free, computationally-efficient, and scale-invariant, enabling large-scale analysis in practice. Moreover, we curate a large and diverse model corpus consisting of major open-source LLM families, and use it to systematically benchmark spectral and non-spectral metrics across models and downstream tasks. We show that our spectral signature supports the tracking of the model lineage, the unsupervised clustering of similar models, and the quantification of the model performance. Overall, the proposed spectral signature provides a meaningful proxy for broad performance trends across LLMs, enabling efficient organization, comparison, and analysis of large model collections.

Current benchmarks for evaluating large language models (LLMs) in medical calculation are largely based on simplified settings, where each patient case corresponds to a single calculator and the required tool is explicitly specified in the query. However, real clinical scenarios often require multiple calculators for joint evaluation, nested-scale calculation, and fuzzy queries that do not directly specify the target calculator. To this end, we propose a new medical calculation benchmark, MedCalc-Pro, which covers three progressively challenging task settings: single-calculator, multi-calculator, and nested-calculator calculation settings. MedCalc-Pro contains 2,268 real-world clinical cases, covering 77 medical calculators across 14 clinical departments. Meanwhile, to address the limited performance of existing frameworks and methods in complex clinical scenarios, we further propose a more generalizable agent framework that supports multi-tool selection and nested-tool calling, while suppressing parameter error propagation through structured validation and evidence review. We conduct systematic comparisons across open-source, closed-source, and medical-specialized LLMs, and the results show that our framework achieves the best performance across all three task settings. This work provides a new benchmark and method for evaluating and applying LLMs in challenging medical calculation scenarios.

We study LLM benchmark coreset selection: selecting a small subset of prompts over multiple benchmarks whose induced model scores and rankings approximate those obtained from the full benchmark suite. In evaluation-unsupervised benchmark coreset selection (our approach), the selection algorithm uses no model evaluation outcomes, and operates on a fine granularity by producing subsets of prompts over multiple benchmarks rather than producing a sub-collection of entire benchmarks. We use submodular subset selection, and we develop and evaluate many different submodular functions for this purpose, including determinantal point process (DPP) based approaches, submodular mutual information functions, and facility location-based functions. On a new large-scale suite of 35 heterogeneous benchmarks spanning five different capability categories, 18 frontier LLMs, and over 61K prompts, we find that the facility location (FL) function operating exclusively on inexpensive semantic prompt embeddings preserves LLM scores better than twelve separate score-based and diversity-based baselines, across a range of coreset budgets. Moreover, we show our proposed objective is not limited to the evaluation-unsupervised regime: in the setting where only a handful of whole benchmarks must be selected and a large amount of model scores are available, the same objective matches or outperforms state-of-the-art baselines on the MMLU and MTEB leaderboards, while being substantially cheaper to compute. Together, our results suggest that submodularity, in general, is a strong and reliable tool for benchmark compression.

LLM-as-a-Judge has become the dominant evaluation paradigm for many natural language generation tasks (albeit mostly in English) due to shortcomings of conventional metrics and high correlations with human judgment. There are now attempts to extend LLM-as-a-Judge to multilingual settings including low-resource languages. However, LLMs have limited proficiency in low-resource languages, and there is often no adequate human validation in these settings. To highlight the scope of the problem and current practices, we explore the use of LLM-as-a-Judge evaluators in ACL Anthology papers focusing on multilingual settings and low-resource languages across a diverse set of tasks. Out of 650 papers mentioning LLM-as-a-judge, only 33 of them focus on low-resource or multilingual settings. Our in-depth analysis of these papers indicates inconsistent evaluation outcomes, a tendency to overtrust LLM judgments in multilingual settings, and the widespread reliance on a single judge model per study. To help the NLP community further, we conclude with a checklist of recommendations about how to use LLM-as-a-Judge in multilingual and low-resource settings

Large language models (LLMs) are increasingly used as cheap, scalable judges that compare candidate outputs pairwise -- to rank responses, select models, or triage papers. Yet LLM judges are both noisy and systematically biased: they favor verbose or well-formatted answers and exhibit position effects, so simply aggregating their votes recovers a ranking of presentation, not of true quality. We study the practical goal of identifying the \topk{} items under a fixed comparison budget, and make two contributions. First, we cast judging as Bayesian inference over latent quality with explicit, judge-specific bias covariates (verbosity, position), regularized by a shrinkage prior so that the data decide which biases a given judge actually exhibits. Second, we introduce a \topk-aware active acquisition rule that chooses the next comparison to maximally reduce uncertainty about \topk{} \emph{membership}, rather than about the full ranking. On a controlled benchmark with known ground-truth quality, judged by sixteen real LLMs spanning open and proprietary families (Llama, Qwen, Phi-4, GPT-4o-mini/5.1/5.5, Gemini, DeepSeek, and Claude Haiku/Sonnet/Opus), naive aggregation plateaus at a wrong \topk{} on biased judges regardless of budget, while our bias-aware model recovers it; \topk-aware acquisition reaches this ceiling with far fewer comparisons than round-robin or a global-uncertainty (D-optimal) rule. Bias is real but heterogeneous and capability-dependent: cheap and mid-tier judges carry a strong verbosity bias that our model corrects (lifting recall from \sim$$0.5--$0.6$ to $0.84$--$1.0$), whereas the frontier judges we tested show little bias and already rank accurately, so bias-aware modeling changes little there.

Large Language Models are increasingly deployed in emotional-support contexts and crisis-related situations. Nevertheless, their cross-lingual abilities in these circumstances remain underexplored. Existing benchmarks emphasize multilingual performance but rarely examine crisis-related empathy and cultural grounding in low-to-mid-resource languages. We introduce SPLIT, a 500-prompt benchmark designed to evaluate LLM consistency in generating emotionally grounded responses across five categories: Stress, Panic, Loneliness, Internal Displacement, and Tension. We evaluate three technically diverse LLMs across three dimensions: Empathetic Accuracy, Linguistic Naturalness, and Contextual & Cultural Grounding. The framework aims to assess and compare the quality of LLM responses in both English and Ukrainian languages, as well as to explore the reliability of the LLM-as-a-jury paradigm. Our findings reveal that Gemini-2.5-Flash and LLaMA-3.3-70B-Instruct degrade when transitioning to Ukrainian, while DeepSeek-V3 remains comparatively stable within our benchmark. We additionally find that human and AI evaluators agree weakly on empathy and naturalness but diverge on cultural grounding. We further argue that producing Ukrainian text is not equivalent to producing Ukrainian emotional support. Our findings may assist in the future development of more culturally tailored benchmark designs, as well as encourage a stronger emphasis on human-centered evaluation.

Reliable reward and preference signals are critical for evaluating and optimizing large language models on open-ended tasks. Rubric-based judges offer a transparent way to decompose such judgments into explicit evaluation criteria, but existing annotation-free rubric generators typically rely on a single generic evaluator. As a result, they may overlook important dimensions of human preference, a failure mode we term dimensional blind spots. To address this limitation, we propose Multi-Role Rubric Generation (MRRG), a training-free and reference-free framework that elicits evaluation criteria from multiple complementary roles and consolidates them into an auditable rubric-based scorer. This scorer can be used both to validate pairwise preferences and to provide rewards for GRPO-style Reinforcement Learning with Verifiable Rewards (RLVR). Experiments on preference validation benchmarks show that MRRG consistently outperforms single-role rubric generation baselines across multiple backbone models. Further RLVR experiments demonstrate that MRRG yields a stronger reward signal for improving open-ended generation.

Public LLM leaderboards optimise for global average performance and do not capture the specific cognitive demands of financial-services work: a model that leads on MMLU-Pro may underperform on document-grounded compliance reasoning, and a coding leader may handle multi-turn customer interactions poorly. We present a meta-benchmarking framework that organises 452 publicly reported benchmarks into 41 O*NET Generalized Work Activities and aggregates those into 38 BIAN banking business domains spanning sales, operations, risk, and support work. A multiplicative weighting scheme (discrimination x coverage x recency), computed over a rolling model window, rewards benchmarks that still separate the best models, are widely reported, and remain in active use, suppressing saturated legacy tests automatically. These weights scale the K-factor in a pairwise Elo tournament, producing cross-benchmark-comparable work-activity scores without raw score normalisation; business-domain scores are weighted averages of the constituent work-activity Elos. We demonstrate the framework on a point-in-time public snapshot covering 288 models across 25 organisations as of June 2026, and describe the methodology, full taxonomy, design decisions, and limitations with the aim of making the approach reproducible for institutions facing similar selection and governance challenges.

We introduce ISOSCI, a benchmark of isomorphic cross-domain science problem pairs that separates reasoning ability from domain knowledge retrieval in LLM evaluation. Each pair shares identical logical structure but requires different domain-specific knowledge, enabling controlled attribution of reasoning-mode gains. Across five model pairs spanning four model families, we find that 91.3% of reasoning-mode gains are knowledge-dependent rather than structure-invariant (63/69 gains; Wilson 95% CI [82.3%, 96.0%]), directly challenging the assumption that chain-of-thought reasoning improves short-horizon procedural scientific problem-solving. Reasoning toggles on highly capable models provide less than 5 percentage points accuracy gain across all domains, and a reasoning-specialized model (o3-mini) that outperforms its standard counterpart on GPQA Diamond (+19.2 percentage points) underperforms on ISOSCI (-24.7 percentage points), showing that benchmark choice determines conclusions about reasoning utility. We release ISOSCI at https://huggingface.co/datasets/isosci/isosci

When should an AI system's answer be trusted? Formal proof assistants offer certainty but cannot reach most of the problem distribution; scalar LLM judges offer coverage but produce opaque scores that cannot be audited after the fact and are subject to the same coherence issues as any LLM. We present Theoria, a verification architecture that closes this gap. A candidate solution is rewritten into a sequence of typed state transitions, each licensed by an explicit justification, whether that be a citation, computation, or problem-given fact, and every transition is independently auditable. The foundational invariant is completeness of change: every difference between consecutive proof states must be accounted for, so hidden premises surface as unlicensed mutations rather than passing silently. On HLE-Verified Gold (185 text-only expert problems), Theoria certifies 105 at 91.4% strict precision (Wilson 95% CI [84.5%, 95.4%]). Every certification produces a human readable proof trace in which each step can be independently challenged. Holistic LLM judges achieve comparable precision at matched coverage but fail on different problems (Jaccard 0.14-0.36), making the approaches complementary. On 95 adversarial poisoned proofs across 15 domains, structured judges catch 94.7% versus 83.2% for holistic judging (p= 0.0017). The overall 11.5 pp gap concentrates in hidden premises (90.6% vs. 62.5%, a 28 pp difference) and fabricated citations (100% vs. 90%), the error classes where the formal analysis predicts an advantage; performance is identical on arithmetic and theorem-misapplication errors, where no advantage is predicted. On GPQA Diamond (n= 65), certified precision is 97.1% (Wilson CI [85.1%, 99.5%]).