LLM Evaluation

LLM: Large Language Model

Follow this topic Ask about this topic

The field studies how to measure language-model capabilities, reliability, and risks, and whether those measurements support sound comparisons and deployment decisions. Approaches include curated and synthetic benchmarks, psychometric and adaptive testing, execution-based checks, robustness tests, and human or LLM-based judges. Researchers also examine calibration, uncertainty, contamination, prompt sensitivity, and whether scores reflect the intended capability across languages and domains. A central tension is that efficient aggregate scores can hide important errors and measurement biases, while more realistic, human-grounded evaluations are costly and difficult to standardize.

Latest papers

2,446 papers231 papers in the last four weeks, down 17% on the four weeks before. 1.5% of all new papers.

May 7, 2026

More Aligned, Less Diverse? Analyzing the Grammar and Lexicon of Two Generations of LLMs

This study contributes to a growing line of research in comparing LLM-generated texts with human-authored text, in this case, English news text. We focus in particular on the evaluation of syntactic properties through formal grammar frameworks. Our analysis compares two generations of LLMs in the context of two human-authored English news datasets from two different years. Employing the Head-Driven Phrase Structure Grammar (HPSG) formalism, we investigate the distributions of syntactic structures and lexical types of AI-generated texts and contrast them with the corresponding distributions in the human-authored New York Times (NYT) articles. We use diversity metrics from ecology and information theory to quantify variation in grammatical constructions and lexical types. We show that English news text has changed little in the given time frame, while newer LLMs display reduced syntactic and, especially, lexical diversity compared to older, non-instruction-tuned models. These findings point to future work in studying effects of instruction tuning, which, while enhancing coherence and adherence to prompts, may narrow the expressive range of model output.

Adrián Gude, Roi Santos-Ríos, Francis Bond +3

Universidade da Coruña, CITIC · Palacký University, Olomouc · Independent Researcher

May 7, 2026

Strat-LLM: Stratified Strategy Alignment for LLM-based Stock Trading with Real-time Multi-Source Signals

Large Language Models (LLMs) are evolving into autonomous trading agents, yet existing benchmarks often overlook the interplay between architectural reasoning and strategy consistency. We propose Strat-LLM, a framework grounded in Stratified Strategy Alignment. Operating in a live-forward setting throughout 2025, it integrates heterogeneous data including sequential prices, real-time news, and annual reports to eliminate look-ahead bias. Extensive stress tests on A-share and U.S. markets reveal: (1) reasoning-heavy models achieve peak utility in Free Mode via internal logic, whereas standard models require Strict Mode as a vital risk anchor; (2) alignment utility is regime-dependent, with Free and Guided modes capturing momentum in uptrending markets, while Strict Mode mitigates drawdowns in downtrends; (3) mid-scale models (35B) show optimal fidelity under strict constraints, whereas ultra-large models (122B) suffer an alignment tax under rigid rules but gain a performance premium in Guided Mode; (4) standard LLMs often fall into a high win-rate trap, optimizing for small gains at the expense of total returns, which can only be mitigated through deep reasoning or strict external guardrails. Project details are available at https://Strat-LLM.github.io.

Wenliang Huang, Zengyi Yu

School of Economics Zhejiang University of Technology Hangzhou, China · Faculty of Education East China Normal University Shanghai, China

LLM Evaluation LLM Alignment LLM Agents Algorithmic Trading

May 7, 2026

Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking

Adaptive prompt and program search makes LLM evaluation selection-sensitive. Once benchmark items are reused inside tuning, the observed winner's score need not estimate the fresh-data performance of the full tune-then-deploy procedure. We study inference for this procedure-level target under explicit tuning budgets. We propose SIREN, a selection-aware repeated-split reporting protocol that freezes the post-search shortlist, separates splitwise selection from held-out evaluation, and uses an item-level Gaussian multiplier bootstrap for uncertainty quantification. In a fixed-shortlist regime with smooth stabilized selection, the estimator admits a first-order item-level representation, and the bootstrap yields valid simultaneous inference on a finite budget grid. This supports confidence intervals for procedure-performance curves and pre-specified equal-budget and cross-budget comparisons. Controlled simulations and MMLU-Pro tuning experiments show that winner-based reporting can be optimistic and can change deployment conclusions, while SIREN remains close to the finite-sample reporting target.

Yang Xu, Jiefu Zhang, Haixiang Sun +3

Purdue University · Johns Hopkins University · Purdue University, USA

LLM Evaluation Selective Inference Benchmark Design Benchmark Validity

May 7, 2026

Logic-Regularized Verifier Elicits Reasoning from LLMs

Verifiers are crucial components for enhancing modern LLMs' reasoning capability. Typicalverifiers require resource-intensive superviseddataset construction, which is costly and faceslimitations in data diversity. In this paper, wepropose LOVER, an unsupervised verifier regularized by logical rules. LOVER treats theverifier as a binary latent variable, utilizinginternal activations and enforcing three logical constraints on multiple reasoning paths:negation consistency, intra-group consistency,and inter-group consistency (grouped by thefinal answer). By incorporating logical rulesas priors, LOVER can leverage unlabeled examples and is directly compatible with any offthe-shelf LLMs. Experiments on 10 datasetsdemonstrate that LOVER significantly outperforms unsupervised baselines, achieving performance comparable to the supervised verifier(reaching its 95% level on average). The sourcecode is publicly available at https://github.com/wangxinyufighting/llm-lover.

Xinyu Wang, Changzhi Sun, Lian Cheng +4

Department of Computer Science and Technology, East China Normal University · Institute of Artificial Intelligence (TeleAI), China Telecom

LLM Evaluation LLM Answer Verification Reasoning Consistency in Language Models LLM Reasoning

May 7, 2026

CITE: Anytime-Valid Statistical Inference in LLM Self-Consistency

Large language models often improve reasoning by sampling multiple outputs and aggregating their final answers, but precise and efficient control of error levels remains a challenging task. In particular, deciding when to stop sampling remains difficult when the stopping rule is data-dependent and the set of possible answers is not known in advance. We study anytime-valid certification of a prespecified target answer as the unique mode of the model's response distribution, a guarantee distinct from answer correctness. We propose the Certification by Intersection-union Testing with E-processes (CITE) algorithm, which provably controls false certification at any prescribed level under arbitrary data-driven stopping, without requiring prior knowledge of the answer category set. We also prove an category-set-size-free stopping-time rate, establish matching minimax lower bounds up to constants in the main regime, and extend the construction to confidence-weighted voting. Simulations and LLM self-consistency experiments show empirical error control and improved certification in diffuse-tail settings.

Hirofumi Ota, Naoto Iwase, Yuki Ichihara +2

arXiv:2605.05873v1

LLM Evaluation Anytime-Valid Inference Sequential Hypothesis Testing Statistical Hypothesis Testing

May 7, 2026

What Makes a Latent Thought Valid? Defining and Auditing Thought Representations in LLMs

Chain-of-Thought (CoT) reasoning improves the performance of Large Language Models (LLMs), yet it writes steps as text and follows one reasoning path at a time, which limits the capabilities of such models. Latent reasoning methods replace these steps with continuous thought representations and claim that a thought representation substitutes for the written reasoning, compresses trajectories, distinguishes semantic content, and achieves superposition of multiple exploration paths at once. These claims concern the content of the thought representation, whereas the evaluations of these methods rely on downstream task accuracy, token counts, and analyses specific to each method. We formalize these claims as a valid thought representation space and prove that a space is valid if and only if its thought representations attain four properties, namely causality, minimality, separability, and stability, each of which follows from one claim. Translating these properties into four measures and auditing three training-free and three trained methods shows gaps in these claims that accuracy may not necessarily reveal. Training-free methods fail all four properties and do not encode the reasoning they are meant to replace, whereas trained methods generally improve substitution. The four properties and measures therefore provide a theoretically grounded evaluation beyond downstream task accuracy and expose failure modes that may guide future development of latent reasoning methods.

Fahd Seddik, Fatemeh Fard

Department of Computer Science, University of British Columbia, Kelowna, BC, Canada

LLM Evaluation LLM Interpretability LLM Reasoning

May 7, 2026

I'm Sorry, but I Can't Help with Braille: Revealing Accessibility Failures in State-of-the-Art LLMs

Large Language Models (LLMs) perform strongly on many language tasks, but their capability in structurally constrained, accessibility-critical modalities such as Braille remains unclear. We evaluate state-of-the-art LLMs on bidirectional Korean-Braille translation using a human-annotated dataset. Despite expectations that multilingual, instruction-tuned models can generalize to Braille via text representations, we find consistently poor, unstable outputs and substantial disagreement with human judgments. These results point to missing Braille-aware tokenization and weak alignment between Korean and Braille patterns. In contrast, supervised fine-tuning of a small model (T5-small) on the same data yields large and stable gains over zero-shot and prompted LLM baselines across standard metrics (SacreBLEU, ChrF++, CER, BLEU, ROUGE-L, METEOR, CIDEr). Our findings reveal a systematic limitation of current LLMs and demonstrate the effectiveness of modest task-specific supervision.

Abdullah Abdullah

orinu Inc. Hwaseong, Republic of Korea

LLM Evaluation LLM Fine-Tuning Assistive Technology for Blind and Low-Vision People

May 6, 2026

MRI-Eval: A Tiered Benchmark for Evaluating LLM Performance on MRI Physics and GE Scanner Operations Knowledge

Background: Existing MRI LLM benchmarks rely mainly on review-book multiple-choice questions, where top proprietary models already score highly, limiting discrimination. No systematic benchmark has evaluated vendor-specific scanner operational knowledge central to research MRI practice. Purpose: We developed MRI-Eval, a tiered benchmark for relative model comparison on MRI physics and GE scanner operations knowledge using primary multiple-choice questions (MCQ), with stem-only and primed diagnostic conditions as complementary analyses. Methods: MRI-Eval includes 1365 scored items across nine categories and three difficulty tiers from textbooks, GE scanner manuals, programming course materials, and expert-generated questions. Five model families were evaluated (GPT-5.4, Claude Opus 4.6, Claude Sonnet 4.6, Gemini 2.5 Pro, Llama 3.3 70B). MCQ was primary; stem-only removed options and used an independent LLM judge; primed stem-only tested responses to incorrect user claims. Results: Overall MCQ accuracy was 93.2% to 97.1%. GE scanner operations was the lowest category for every model (88.2% to 94.6%). In stem-only, frontier-model accuracy fell to 58.4% to 61.1%, and Llama 3.3 70B fell to 37.1%; GE scanner operations stem-only accuracy was 13.8% to 29.8%. Conclusion: High MCQ performance can mask weak free-text recall, especially for vendor-specific operational knowledge. MRI-Eval is most informative as a relative comparison benchmark rather than an absolute competency measure and supports caution in using raw LLM outputs for GE-specific protocol guidance.

Perry E. Radau

Department of Radiology, University of Calgary · Child and Adolescent Imaging Research (CAIR) Program · Alberta Children’s Hospital Research Institute +1

LLM Evaluation Healthcare Magnetic Resonance Imaging

May 6, 2026

The Shared Latent Structure of LLM Psychometric Responses

Human psychometric questionnaires are increasingly used to characterize large language models (LLMs), but it remains unclear what exactly their responses reflect. To answer this question we analyze responses from 50 LLMs across 45 questionnaires spanning multiple psychological domains using psychometric methodology. We found a dominant principal component explaining 47.1% of variance across standardized, response-derived questionnaire-level primary scores, revealing substantial shared structure across instruments. We investigate its meaning through semantic analysis, respondent framing, and human annotations. Semantic analysis suggests that the component partly reflects experiential self-attribution: how readily models endorse statements describing subjective states and bodily experiences. A model score emphasizing items whose disagreement decreases under human simulation correlates strongly with the component (

r=0.864

). Human ratings of 289 matched items show that inner-life content is positively associated, and social desirability negatively associated, with item-component correlations after mutual adjustment and controls for other semantic properties. Together, six rated properties explain 22.1% of variance in Fisher-transformed item-component correlations, supporting a partial interpretation involving both experiential self-attribution and socially desirable responding. These findings suggest that LLM psychometric profiles share response tendencies that require interpretation beyond the human traits their questionnaires were designed to measure.

Hubert Plisiecki, Sabina Siudaj, Kacper Dudzic +4

IDEAS Research Institute · University of Warsaw

LLM Evaluation Personality Modeling in Language Models Psychometric Validation

May 6, 2026

Curated AI beats frontier LLMs at pharma asset discovery

General-purpose LLMs with web search are increasingly used to scout the competitive landscape of pharmaceutical pipelines. We benchmark Gosset -- an AI platform with a chat interface backed by curated target-, modality-, and indication-level drug-asset annotations -- against four frontier systems with web access (Claude Opus 4.7, GPT 5.5, Gemini 3.1 Pro, Perplexity sonar-pro) on ten niche oncology/immunology targets where most of the pipeline lives in the long tail of preclinical and Asian-developed assets. All five systems receive the same natural-language query and the same JSON output schema. Across 10 targets Gosset returns 3.2x more verified drugs per query than the best frontier system, at perfect precision and 100% recall against the cross-system union of verified drugs. The same curated index is exposed as a Gosset MCP server that any frontier model can call as a tool, suggesting that each of these systems can close most of the recall gap by swapping generic web search for a curated index behind the same chat interface.

Łukasz Kidziński, Kevin Thomas

Gosset Research

LLM Evaluation Healthcare AI-Assisted Scientific Research LLM Tool Use Drug Discovery

May 6, 2026

BenCSSmark: Making the Social Sciences Count in LLM Research

This position paper argues that the under-representation of social science tasks in contemporary LLM benchmarks limits advances in both LLM evaluation and social scientific inquiry. Benchmarks -- standardized tools for assessing computational systems -- are pivotal in the development of artificial intelligence (AI), including large language models (LLMs). Benchmarks do more than measure progress -- they actively structure it, shaping reputations, research agendas, and commercial outcomes. Despite this central role, the social sciences are largely absent from mainstream evaluation frameworks, even though scholars in these fields generate dozens of rigorously annotated, context-sensitive datasets each year. Integrating this work into benchmark design could significantly improve the generalization and robustness of AI models. In turn, models trained on social scientific tasks would likely yield better performance on classic and contemporary tasks in disciplines as diverse as history, sociology, political science or economics. This is all the more pressing as these disciplines are quickly turning to LLMs for assistance. To address this gap, we introduce BenCSSmark, a benchmark composed of datasets annotated by computational social scientists. By integrating social scientific perspectives into benchmarking, BenCSSmark seeks to promote more robust, transparent, and socially relevant AI systems and to foster efficient collaboration.

Arnault Chatelain, Étienne Ollion, Qianwen Guan +7

CREST (École Polytechnique, ENSAE, CNRS), 5 avenue Le Chatelier, 91120 Palaiseau, France · LLF (Université Paris Cité and CNRS), UFRL Olympe de Gouges, 13 place Paul Ricoeur, 75013 Paris, France · Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG, 38000 Grenoble, France +1

LLM Evaluation Benchmark Design Computational Social Science

May 6, 2026

Paraphrase-Induced Output-Mode Collapse: When LLMs Break Character Under Semantically Equivalent Inputs

When the substantive content of a request is rewritten, do large language models still answer in the format the original task asked for? We find that they often do not, even at temperature zero. On a 150-query evaluation over five compact 2025-era LLMs and four task types, we observe a systematic failure mode we call prompt-variant output-mode collapse: when a closed-form prompt asks for a bare label or a single choice token, content-preserving prompt variants can push the model into conversational prose, the requested format dissolves, and exact-match evaluation pipelines silently misjudge the result. To make this measurable, we release PARACONSIST, a 900-prompt benchmark of 150 base queries with five lexical, syntactic, and semantic-expansion prompt variants each, and a Semantic Consistency Score that decomposes prompt-variant robustness into answer consistency, sentence-BERT semantic similarity, and length stability. Under a whole-word answer-set match, only ~22% of closed-form variant responses preserve the ground-truth label inside their output, while ~78% drift away from the answer space entirely. In our pool, the dominant predictor of collapse is task structure rather than model identity, with model differentiation jointly carried by answer consistency and length stability. Robustness audits should therefore track response-mode preservation as a first-class reliability target alongside answer accuracy.

Aofan Liu, Jingxiang Meng

1Peking University. · University of Chicago.

Prompt Sensitivity LLM Evaluation LLM Reliability Structured Output Generation Language Model Robustness

May 6, 2026

Benchmarking LLMs on the Massive Sound Embedding Benchmark (MSEB)

The Massive Sound Embedding Benchmark (MSEB) has emerged as a standard for evaluating the functional breadth of audio models. While initial baselines focused on specialized encoders, the shift toward "audio-native" Large Language Models (LLMs) suggests a new paradigm where a single multimodal backbone may replace complex, task-specific pipelines. This paper provides a rigorous empirical evaluation of leading LLMs - including members from the Gemini and GPT families - across the eight core MSEB capabilities to assess their efficacy and audio-text parity. Our results indicate that while a significant modality gap persists regarding performance and robustness, the empirical evidence for an "optimal" modeling approach remains inconclusive. Ultimately, the choice between audionative and cascaded architectures depends heavily on specific use-case requirements and the underlying assumptions regarding latency, cost, and reasoning depth.

Cyril Allauzen, Tom Bagby, Georg Heigold +2

Google USA & Germany

Audio-Language Model Evaluation LLM Evaluation Audio Representation Learning Audio-Language Models

May 6, 2026

CANDI: Contextual Alignment for Niche Domains Question Answering

The deployment of large language models (LLMs) in specialized domains like medical diagnostics and financial advisory necessitates evaluating capabilities beyond general knowledge. Traditional question-answering benchmarks often fail to capture the nuanced contextual grounding, user awareness, and domain understanding these fields require. To address this, we introduce CANDI-QA (Contextual Alignment for Niche Domains Question Answering), a novel dataset evaluating LLMs on delivering accurate, context-sensitive, and user-aligned answers in specialized settings. CANDI-QA features expert-curated question-answer pairs structured into two categories: (1) Information Assistance Questions, which are direct, factual queries requiring precise extraction, and (2) Applied Inference Questions, which are multi-hop reasoning tasks needing situational inference to generate actionable insights. We evaluate over ten diverse language models, from compact open-source to state-of-the-art proprietary systems. As a robust baseline, we present MTSS-Net, a lightweight neuro-symbolic framework combining neural retrieval with rule-based reasoning. Our findings highlight the profound challenges of achieving contextual alignment in niche domains, revealing the limitations of current LLMs without enhanced contextual or symbolic integration. Ultimately, CANDI-QA serves as a critical benchmark for advancing research in context-aware language models, stimulating the development of robust, trustworthy AI for high-stakes domains.

Megha Chakraborty, Darssan L. Eswaramoorthi, Het Riteshkumar Shah +5

University of South Carolina · IIIT-Delhi · Indian Institute of Technology Madras

LLM Evaluation LLM Grounding Question Answering

May 6, 2026

How Does Thinking Mode Change LLM Moral Judgments? A Controlled Instant-vs-Thinking Comparison Across Five Frontier Models

We evaluate whether enabling provider-exposed reasoning mode changes moral judgments within the same model checkpoint. Across 100 moral-judgment scenarios and five frontier reasoning-trained LLMs (Claude Sonnet 4.6, GPT 5.5, Gemini 3 Flash, DeepSeek V3.1, and Qwen3.5 397B), aggregate binary-verdict agreement remains high and statistically indistinguishable between instant and thinking modes (Krippendorff's alpha = 0.78 vs. 0.79). However, disagreement is concentrated in 21 model-disputed scenarios, where instant-mode agreement is near chance (alpha = 0.08). On these scenarios, reasoning directionally narrows cross-model disagreement, increasing mean pairwise agreement from 5.4 to 6.7 out of 10. Reasoning also reduces demographic-judgment inconsistency in three of five models and does not increase it for any model. Across all five model families, reasoning changes self-labeled ethical frameworks more often than binary verdicts.

Sai Sourabh Madur

Independent researcher (ex-Meta)

LLM Evaluation Moral Reasoning in Language Models LLM Reasoning Moral Reasoning

May 6, 2026

Deployment-Relevant Alignment Cannot Be Inferred from Model-Level Evaluation Alone

Alignment evaluation in machine learning has largely become evaluation of models. Influential benchmarks score model outputs under fixed inputs, such as truthfulness, instruction following, or pairwise preference, and these scores are often used to support claims about deployed alignment. This paper argues that deployment-relevant alignment cannot be inferred from model-level evaluation alone. Alignment claims should instead be indexed to the level at which evidence is collected: model-level, response-level, interaction-level, or deployment-level. Two studies support this position. First, a structured audit of eleven alignment benchmarks, extended to a sixteen-benchmark corpus, dual-coded against an eight-dimension rubric with Cohen's kappa = 0.87, finds that user-facing verification support is absent across every benchmark examined, while process steerability is nearly absent. The few interactional benchmarks identified, including tau-bench, CURATe, Rifts, and Common Ground, remain fragmented in coverage, and benchmark construction rather than data source determines what is measured. Second, a blinded cross-model stress test using 180 transcripts across three frontier models and four scaffolds finds that the same verification scaffold raises one model's verification support to ceiling while leaving another categorically unchanged. This shows that scaffold efficacy is model-dependent and that the gap identified by the audit cannot be closed at the model level alone. We propose a system-level evaluation agenda: alignment profiles instead of single scores, fixed-scaffolding protocols for comparable interactional evaluation, and reporting templates that make the inferential distance between evaluation evidence and deployment claims explicit.

Varad Vishwarupe, Nigel Shadbolt, Marina Jirotka +1

Department of Computer Science, University of Oxford

LLM Evaluation LLM Alignment LLM Auditing AI Safety Evaluation

May 6, 2026

From Memorization to Creation: Evaluating the Cognitive Depth of LLM-Generated Educational Questions

While LLMs show promise in automating educational content creation, their ability to generate questions that stimulate higher-order thinking remains understudied. This work evaluates six widely-used LLMs through a Bloom's Taxonomy lens, focusing on their capacity to transcend rote memorization and achieve cognitive leaps. Using a hybrid human--AI evaluation protocol, we generate and analyze 20{,}700 questions across computer science, K--12 math, and social-science domains. Key contributions include: (1) a fine-grained prompting strategy that reduces question repetitiveness by 24.45% for Qwen2.5-7B-Instruct, and increases the proportion of higher-order cognitive level outputs by 11.53% for InternLM3-8B-Instruct; (2) quantitative metrics for cognitive shift intensity (CogShift) and category drift, revealing InternLM3's superior performance in multi-level transitions; (3) an interpretability analysis revealing metric-level correlations that enhance the transparency of Chain-of-Thought prompting. Our findings highlight the importance of cognitive-aware prompt design and provide benchmarks for deploying LLMs in personalized learning systems.

Xiaolong Wang, Zhe Zhao, Song Lai +5

Squirrel Ai Learning Shanghai, China · City University of Hong Kong Hong Kong, China · Zhejiang Normal University Squirrel Ai Learning Jinhua, China +2

LLM Evaluation LLM Prompting Generative AI in Education

May 5, 2026

Evaluating Advanced Prompting on Gemini Flash for Multi-Hop Biomedical QA

The MedHopQA challenge presents a critical test for Large Language Models (LLMs): complex, multi-hop reasoning in the high-stakes biomedical domain. This paper details our direct API-based evaluation of Google's Gemini Flash models, focusing on the impact of advanced prompt engineering. We designed a sophisticated, multi-component prompt for Gemini 2.0 Flash that combined role-playing, explicit multi-shot Chain-of-Thought (CoT) examples, and detailed formatting rules. Our best run, using this complex prompt, achieved a Concept Level Score of 0.720. This result dramatically outperformed a baseline prompt which scored only 0.565. Remarkably, this performance on the efficient Gemini 2.0 Flash was almost identical to the result from the next-generation Gemini 2.5 Flash. Our findings demonstrate that sophisticated prompt design is a critical factor for unlocking the full reasoning capabilities of modern LLMs.

Ahmed Bajaber, Mohammed Alliheedi

1Saudi Med AI Lab (SMAIL) 2Prince Sultan University, Riyadh, Saudi Arabia · 2Prince Sultan University, Riyadh, Saudi Arabia · 3Al-Baha University, Al Baha, Saudi Arabia

Multi-Hop QA LLM Evaluation LLM Prompting Biomedical QA Few-Shot Prompting

May 5, 2026

Towards Self-Referential Analytic Assessment: A Profile-Based Approach to L2 Writing Evaluation with LLMs

Automated essay scoring (AES) research often relies on rank-based correlation metrics to validate analytic assessment. However, such metrics obscure both intrinsic intercorrelations among analytic dimensions that arise from the structure of writing proficiency itself and halo effects, whereby holistic impressions bleed into fine-grained component scores. As a result, high correlations may mask a system's true diagnostic behaviour. In this study, we propose a novel self-referential assessment evaluation framework that focuses on identifying intra-learner strengths and weaknesses rather than assessing inter-learner rankings. We conduct experiments on the publicly available ICNALE GRA, a uniquely dense second-language writing dataset annotated holistically and analytically by up to 80 trained raters. To obtain reliable reference scores, we apply two-facet Rasch modelling to calibrate rater severity and derive fair average scores across ten analytic aspects and holistic proficiency. We compare the analytic scoring performance of human operational raters and three large language models (LLMs) in a zero-shot setting. Our results show that LLMs tend to outperform single human raters in identifying relative weaknesses (negative feedback) across several proficiency aspects, while human raters remain stronger at identifying relative strengths (positive feedback). Overall, our findings highlight the limitations of rank-based evaluation for analytic assessment and demonstrate the value of intra-learner, profile-based methods for assessing and deploying LLMs in AES.

Stefano Bannò, Kate Knill, Mark Gales

ALTA Institute, Department of Engineering, University of Cambridge (UK)

LLM Evaluation Automated Essay Scoring Psychometric Validation

May 5, 2026

ReplaySCM: A Benchmark for Executable Causal Mechanism Induction from Interventions

Most causal benchmarks for language models score local answers or graph structure. We introduce ReplaySCM, a 1,300 item benchmark for executable causal mechanism induction from finite interventional evidence. Each item contains binary worlds generated by a latent fully observed acyclic Boolean structural causal model (SCM). A system must output a mechanism map in a restricted Boolean DSL; the submission is parsed, checked for legality and acyclicity, and replayed on training and held-out intervention worlds. Scoring uses replay behavior rather than formula strings, so syntactically different mechanisms receive credit when they behave correctly. ReplaySCM varies the structural information disclosed to the model through Ordered, Block-order, Hidden-order, and Hidden-roots settings, and includes Alternative-SCM tasks that supply a valid reference SCM and ask for a semantically distinct alternative that fits the training worlds, together with a separating intervention and witness. Frontier LLMs infer parts of the functional-parent structure, but held-out replay drops sharply when order or root structure is hidden. We also evaluate a matched support-audit ladder: Original, Extra Worlds, and Counterexample Audit (CEx), that raises mean local predecessor-pattern coverage from 0.8949 to 0.9815 to 1.0; under the audited searches, no discovered semantic alternative remains consistent with the training worlds. The Ordered/Hidden-order gap persists under this stronger evidence. ReplaySCM complements answer-level causal reasoning and graph-discovery benchmarks by evaluating executable replay generalization from finite interventional evidence, without claiming unique identification of the latent SCM.

Serafim Batzoglou

LLM Evaluation Structural Causal Models Causal Interventions in Language Models

May 5, 2026

Not All That Is Fluent Is Factual: Investigating Hallucinations of Large Language Models in Academic Writing

Large Language models (LLMs) show extraordinary abilities, but they are still prone to hallucinations, especially when we use them for generating Academic content. We have investigated four popular LLMs, ChatGPT, Grok, Gemini, and Copilot for hallucinations specifically for academic writing. We have designed 80 prompts across four categories, namely, reference generation, factual explanation, abstract generation, and writing improvement. We evaluated the model using a 0-5 rubric score, which checks factual accuracy, reference validity, coherence, style consistency, and academic tone. A novel weighted metric, Hallucination Index (HI), was introduced to measure hallucination in the responses generated by the models. Some of the most widely used evaluation metrics often fail to check errors which alter sentiment in machine-translated text. We found that Grok and Copilot perform better on reference generation tasks, but they often struggle with abstract or stylistic prompts, with HI values of 0.67 and 0.70, respectively. Whereas, Gemini and ChatGPT have done well with having stronger tone control, but they lack in writing factual tasks and higher hallucination risk with HI scores of 0.53 and 0.57, respectively. Our study found that hallucination behavior does not depend solely on model architecture but also on the type of task and the prompting conditions we are providing. We propose that our work opens new research dimensions for future researchers.

Humam Khan, Md Tabrez Nafis, Shahab Saquib Sohail +2

Department of Computer Science and Engineering, SEST Jamia Hamdard New Delhi, India · Energy, Resources and Industry WSP Calgary, Canada

LLM Evaluation LLM Prompting Hallucination in Language Models

May 5, 2026

Frontier Lag: A Bibliometric Audit of Capability Misrepresentation in Academic AI Evaluation

LLM evaluations in applied domains tend to reflect models that were already outclassed at time of publication. We observe a publication elicitation gap: the distance between the AI systems generating the results reported in an academic paper and the AI systems that a current reader of that paper would reasonably assume are being referenced. We systematically sweep OpenAlex from 2022-01-01 to 2026-04-01 (n = 112,303 LLM keyword matches). Then, we identify what models were evaluated (n = 18,574 admissible records). We then rank each evaluated LLM against a frontier LLM based on the Epoch AI Capabilities Index (ECI), an aggregate LLM capability score. We find that the median paper's models are worse than the frontier LLM at the time of evaluation (a median gap of +10.45 ECI; H1, n = 12,668). The gap is increasing at a rate of +4.07 ECI per year (H2, nominal 95% CI [+3.75, +4.45]). An explicitly stated evaluation date can be found in only 18.4% of full-text papers. A Bayes-corrected 52.5% (95% CI: [47.3, 57.9]) of the abstracts audited discuss their conclusions in terms of "AI" as a category, rather than specific models. Just 2.2% of abstracts and 21.2% of full-text articles evaluating reasoning models disclose whether the models were tested with reasoning turned on or off (H4). We propose a solution to this problem that is distributed among authors, editors, and funders. First, reporting from authors; VERSIO-AI v1.2 is a proposed 13-item checklist to cover the configuration surface described herein. Second, enforcement from journal editors and peer reviewers. Third, conditioning grants on disclosure and providing API access.

David Gringras, Misha Salahshoor

Harvard University · AISST, Cambridge, MA

LLM Evaluation LLM Auditing

May 5, 2026

The Counterexample Game: Iterated Conceptual Analysis and Repair in Language Models

Conceptual analysis -- proposing definitions and refining them through counterexamples -- is central to philosophical methodology. We study whether language models can perform this task through iterated analysis and repair chains: one model instance generates counterexamples to a proposed definition, another repairs the definition, and the process repeats. Across 20 concepts and thousands of counterexample-repair cycles, we find that, although many LM-generated counterexamples are judged invalid by both expert humans and an LM judge, the LM judge accepts roughly twice as many as humans do. Nonetheless, per-item validity judgments are moderately consistent across humans and between humans and the LM. We further find that extended iteration produces increasingly verbose definitions without improving accuracy. We also see that some concepts resist stable definitions in general. These findings suggest that while LMs can engage in philosophical reasoning, the counterexample-repair loop hits diminishing returns quickly and could be a fruitful test case for evaluating whether LMs can sustain high-level iterated philosophical reasoning.

Daniel Drucker, Kyle Mahowald

Department of Philosophy The University of Texas at Austin · Department of Linguistics The University of Texas at Austin

LLM Self-Correction LLM Evaluation Counterexample-Guided Refinement LLM Reasoning

May 5, 2026

EvoLM: Self-Evolving Language Models through Co-Evolved Discriminative Rubrics

Language models encode substantial evaluative knowledge from pretraining, yet current post-training methods rely on external supervision (human annotations, proprietary models, or scalar reward models) to produce reward signals. Each imposes a ceiling. Human judgment cannot supervise capabilities beyond its own, proprietary APIs create dependencies, and verifiable rewards cover only domains with ground-truth answers. Self-improvement from a model's own evaluative capacity is a reward source that scales with the model itself, yet remains largely untapped by current methods. We introduce EVOLM, a post-training method that structures this capacity into explicit discriminative rubrics and uses them as training signal. EVOLM trains two capabilities within a single language model in alternation: (1) a rubric generator producing instance-specific evaluation criteria optimized for discriminative utility, which maximizes a small frozen judge's ability to distinguish preferred from dispreferred responses; and (2) a policy trained using those rubric-conditioned scores as reward. All preference signals are constructed from the policy's own outputs via temporal contrast with earlier checkpoints, requiring no human annotation or external supervision. EVOLM trains a Qwen3-8B model to generate rubrics that outperform GPT-4.1 on RewardBench-2 by 25.7%. The co-trained policy achieves 69.3% average on the OLMo3-Adapt suite, outperforming policies trained with GPT-4.1 prompted rubrics by 3.9% and with the state-of-the-art 8B reward model SkyWork-RM by 16%. Overall, EVOLM demonstrates that structuring a model's evaluative capacity into co-evolving discriminative rubrics enables self-improvement without external supervision.

Shuyue Stella Li, Rui Xin, Teng Xiao +8

University of Washington · 2Allen Institute for AI · University of Pennsylvania

RL for Language Models LLM Evaluation Language Model Generation Evaluation Self-Training for Language Models Language Model Self-Assessment Language Model Post-Training+1

May 5, 2026

MCJudgeBench: A Benchmark for Constraint-Level Judge Evaluation in Multi-Constraint Instruction Following

Multi-constraint instruction following requires verifying whether a response satisfies multiple individual requirements, yet LLM judges are often assessed only through overall-response judgments. We introduce MCJudgeBench, a benchmark for constraint-level judge evaluation in multi-constraint instruction following. Each instance includes an instruction, a candidate response, an explicit constraint list, per-constraint gold labels in {yes, partial, no}, and controlled response-side perturbations. The evaluation protocol further includes evaluation prompt variants to test judge stability. We evaluate proprietary and open-source LLM judges using both correctness and inconsistency metrics, distinguishing intrinsic inconsistency under stochastic decoding from procedural inconsistency under prompt and response perturbations. Our results show that judge reliability has multiple dimensions: strong overall performance does not guarantee equally reliable detection across label categories, especially for rarer partial and no cases. Judges with higher correctness do not always have lower inconsistency. Evaluation with reasoning improves correctness but does not uniformly improve stability. These findings motivate evaluating LLM judges at the constraint level to study these failure modes.

Jaeyun Lee, Junyoung Koh, Zeynel Tok +2

University of Oxford · Yonsei University

LLM Evaluation LLM-as-a-Judge Instruction Following LLM Reliability

May 5, 2026

TriBench-Ko: Evaluating LLM Risks in Judicial Workflows

Large language models (LLMs) are increasingly integrated into legal workflows. However, existing benchmarks primarily address proxy tasks, such as bar examination performance or classification, which fail to capture the performance and risks inherent in day-to-day judicial processes. To address this, we publicly release TriBench-Ko, a Korean benchmark designed to evaluate potential deployment risks of LLMs within the context of verified judicial task requirements. It covers four core tasks: jurisprudence summarization, precedent retrieval, legal issue extraction, and evidence analysis. It jointly assesses model behavior across multiple deployment risk categories, including inaccuracy (hallucination, omission, statutory misapplication), biases (demographic, overcompliance), inconsistencies (prompt sensitivity, non-determinism), and adjudicative overreach. Each item is structured to systematically assess both task performance and a specific risk type based on real judicial decisions. Our evaluation of a range of contemporary LLMs reveals that many models frequently manifest significant risks, most notably struggling with precedent retrieval and failing to capture critical legal information. We provide a comprehensive diagnosis of these LLMs and pinpoint critical areas where LLM-generated outputs in judicial contexts necessitate rigorous inspection and caution. Our dataset and code are available at https://github.com/holi-lab/TriBench-Ko

Haesung Lee, Gyubin Choi, Eun-Ju Lee +5

Center for Trustworthy AI, Seoul National University · Graduate School of Data Science, Seoul National University · Responsible AI Team, KT +1

LLM Evaluation Language Model Safety Evaluation Language Model Bias Evaluation Language Model Robustness

May 5, 2026

OracleProto: A Reproducible Framework for Benchmarking LLM Forecasting via Knowledge Cutoffs and Temporal Masking

Forecasting is a composite capability encompassing information gathering, evidence integration, situational assessment, and decision-making. Large language models (LLMs) combine reasoning and tool use, offering new avenues for automated forecasting and decision support. Yet LLM forecasting evaluation faces a structural challenge: live benchmarks support prospective assessment, but limited question reuse and changing information conditions make results difficult to reproduce and compare; retrospective benchmarks offer reproducibility but risk information leakage. We introduce OracleProto, a reproducible framework for evaluating LLM forecasting in a controlled, temporally masked environment. Through model knowledge cutoff constraints and temporal masking, OracleProto constructs a temporal sandbox for real-world web retrieval, audits information boundaries through leakage detection, and reconstructs resolved events as forecasting instances. Discrete answer normalization and hierarchical scoring enable unified evaluation. We evaluate 27 model-configuration pairs on 300 FutureX-Past-derived questions over 24,300 prediction trials, assessing forecasting quality, sampling stability, and cost efficiency under controlled information boundaries. An audit finds only 1.37% residual leakage in retrieval results after temporal masking and leakage filtering. OracleProto retains resolved forecasting tasks as reusable evaluation resources under explicit temporal boundaries, supporting continual accumulation of forecasting datasets and systematic evaluation of forecasting capabilities. Code is available at https://anonymous.4open.science/r/OracleProto-2E3A/.

Yiding Ma, Chengyun Ruan, Kaibo Huang +3

Beijing University of Posts and Telecommunications

LLM Evaluation Forecasting Benchmarks LLM-Based Time Series Forecasting Temporal Data Leakage

May 5, 2026

PatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination

Patent examination is a complex, multi-stage process requiring both technical expertise and legal reasoning, increasingly challenged by rising application volumes. Prior benchmarks predominantly view patent examination as discriminative classification or static extraction, failing to capture its inherently interactive and iterative nature, similar to the peer review and rebuttal process in academic publishing. In this paper, we introduce PatRe, the first benchmark that models the full patent examination lifecycle, including Office Action generation and applicant rebuttal. PatRe comprises 480 real-world cases and supports both oracle and retrieval-simulated evaluation settings. Our benchmark reframes patent examination as a dynamic, multi-turn process of justification and response. Extensive experiments across various LLMs reveal critical insights into model performance, including differences between proprietary and open-source models, as well as task asymmetries between examiner analysis and applicant-side rebuttal. These findings highlight both the potential and current limitations of LLMs in modeling complex, real-world legal reasoning and technical novelty judgment in patent examination. We release our code and dataset to facilitate future research on patent examination modeling.

Qiyao Wang, Xinyi Chen, Longze Chen +4

Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Dalian University of Technology +2

LLM Evaluation Legal Document Analysis Text Generation

May 5, 2026

Revisiting Graph-Tokenizing Large Language Models: A Systematic Evaluation of Graph Token Understanding

The remarkable success of large language models (LLMs) has motivated researchers to adapt them as universal predictors for various graph tasks. As a widely recognized paradigm, Graph-Tokenizing LLMs (GTokenLLMs) compress complex graph data into graph tokens and treat them as prefix tokens for querying LLMs, leading many to believe that LLMs can understand graphs more effectively and efficiently. In this paper, we challenge this belief: Do GTokenLLMs fully understand graph tokens in the natural-language embedding space? Motivated by this question, we formalize a unified framework for GTokenLLMs and propose an evaluation pipeline, GTEval, to assess graph-token understanding via instruction transformations at the format and content levels. We conduct extensive experiments on 6 representative GTokenLLMs with GTEval. The primary findings are as follows: (1) Existing GTokenLLMs do not fully understand graph tokens. They exhibit over-sensitivity or over-insensitivity to instruction changes, and rely heavily on text for reasoning; (2) Although graph tokens preserve task-relevant graph information and receive attention across LLM layers, their utilization varies across models and instruction variants; (3) Additional instruction tuning can improve performance on the original and seen instructions, but it does not fully address the challenge of graph-token understanding, calling for further improvement.

Zhongjian Zhang, Yue Yu, Mengmei Zhang +3

Beijing University of Posts and Telecommunications · China Telecom Bestpay · Beihang University

LLM Evaluation LLM Reasoning with Graphs Graph Foundation Models LLMs for Graph Learning

May 5, 2026

Revisiting the Travel Planning Capabilities of Large Language Models

Travel planning serves as a critical task for long-horizon reasoning, exposing significant deficits in LLMs. However, existing benchmarks and evaluations primarily assess final plans in an end-to-end manner, which lacks interpretability and makes it difficult to analyze the root causes of failures. To bridge this gap, we decompose travel planning into five constituent atomic sub-capabilities, including Constraint Extraction, Tool Use, Plan Generation, Error Identification, and Error Correction. We implement a decoupled evaluation protocol leveraging oracle intermediate contexts to rigorously isolate these components, thereby measuring the atomic performance boundary without the noise of cascading errors. Our results highlight a clear contrast in performance: while LLMs are proficient in extracting explicit constraints, they struggle to infer implicit, open-world requirements. Furthermore, they exhibit structural biases in plan generation and suffer from ineffective self-correction, characterized by excessive sensitivity and erroneous persistence. These findings offer precise directions for improving LLM reasoning and planning abilities.

Bo-Wen Zhang, Jin Ye, Peng-Yu Hua +4

State Key Laboratory of Novel Software Technology, Nanjing University, China · School of Intelligence Science and Technology, Nanjing University, China · School of Artificial Intelligence, Nanjing University, China

LLM Self-Correction LLM Evaluation LLM Planning Travel Planning