LLM Evaluation

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

194 papers in the last four weeks, up 87% on the four weeks before. 1.9% of all new papers.

Jul 13Week of Sep 28

Latest papers 1,643

May 16, 2026cs.CR

The Range Shrinks, the Threat Remains: Re-evaluating LLM Package Hallucinations on the 2026 Frontier-Model Cohort

Spracklen et al. (USENIX Security '25) showed that code-generating large language models hallucinate package names that do not exist on PyPI or npm at rates ranging from 5.2% on commercial models to 21.7% on open-source models, creating an attack surface for slopsquatting -- the registration of malicious packages under hallucinated names. We replicate their methodology on five frontier code-capable LLMs released between October 2025 and March 2026: Claude Sonnet 4.6, Claude Haiku 4.5, GPT-5.4-mini, Gemini 2.5 Pro, and DeepSeek V3.2. Across 199,845 paired Python and JavaScript prompts validated against PyPI and npm master lists, we measure overall hallucination rates between 4.62% (Claude Haiku 4.5) and 6.10% (GPT-5.4-mini) -- an order-of-magnitude compression of the inter-model spread observed by Spracklen, but not a retirement of the threat. Beyond replication, we identify a set of 127 package names (109 on PyPI, 18 on npm) that all five evaluated models invent identically; following coordinated disclosure with PyPI Security and Socket.dev, 53 of these (41 on PyPI, 12 on npm) remain registrable by an attacker after each registry's existing defenses, constituting a model-agnostic supply-chain attack surface that no single-model study can reveal. We further document a Python-over-JavaScript hallucination asymmetry that inverts Spracklen's 2024 finding, identify a Haiku-below-Sonnet inversion within the Anthropic family, and observe a Jaccard-similarity peak between DeepSeek V3.2 and GPT-5.4-mini (J = 0.343) suggestive of shared training-data origins.

Aleksandr Churilov

Independent Researcher

LLM Evaluation Hallucination in Language Models Software Supply Chain Security Code Language Models LLM Code Generation

May 16, 2026cs.CL

PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifacts

Large language models (LLMs) hallucinate with confidence: their outputs can be fluent, authoritative, and simply wrong. In medical, legal, and scientific applications this failure causes direct harm, and detecting it from internal model states offers a path to safer deployment. A growing body of work reports that this problem is increasingly tractable, with recent methods achieving high detection performance on widely used benchmarks. We show, however, that much of this apparent progress does not survive scrutiny. Four of the six corpora embed the ground-truth answer directly in the input prompt. A naïve text-similarity baseline we call \textsc{TxTemb} exploits this to achieve near-perfect detection scores without any access to model internals. To measure what genuine detection capability remains once these artifacts are controlled, we conduct a large-scale evaluation spanning twenty-two detection methods, twelve open-source models spanning six architectural families, and six corpora. We further introduce \textbf{DRIFT}, a supervised probe over inter-layer hidden-state transitions, as a point of comparison for live-generation detection. Our findings suggest that the field's reported progress on hallucination detection is substantially explained by benchmark construction artifacts in widely used corpora, and that the majority of established baselines perform near chance under controlled conditions; the consistent exceptions are SAPLMA and DRIFT, both supervised probes on upper-layer hidden states.

Khizar Hussain, Murat Kantarcioglu

Virginia Tech

LLM Evaluation Language Model Error Detection Hallucination in Language Models LLM Reliability LLM Hallucination Detection Language Model Probing

May 16, 2026cs.CL

HalluScore: Large Language Model Hallucination Question Answering Benchmark

Large language models (LLMs) have achieved remarkable progress in natural language generation, but remain susceptible to hallucination. In response to growing concerns about hallucinations, several benchmarks have been developed, primarily in English and Chinese. However, Arabic remains underrepresented, with limited benchmarks for LLMs hallucination due to scarce annotated resources and the language's morphological complexity. Consequently, existing benchmarks do not adequately reflect the linguistic, cultural, and reasoning characteristics of Arabic. To address this gap, we introduce HalluScore, a structured Arabic question answering benchmark designed to evaluate hallucination behavior in LLMs across different levels of reasoning difficulty, various knowledge domains, historical timelines, and culturally grounded Arabic scenarios. It contains 827 carefully curated questions for evaluating, detecting, and mitigating hallucination in LLMs. The dataset was constructed through a structured pipeline involving quality assurance, filtering for clarity and factual validity, and model-driven selection to retain questions that consistently trigger hallucinations. Each question is linked to verified ground-truth evidence, answer explanations, and multi-label annotations. Using the HalluScore benchmark, we conduct a comprehensive empirical analysis of hallucination patterns across 17 Arabic, multilingual, and reasoning LLMs. Moreover, we provide high-quality human annotations identifying hallucinated, non-hallucinated, and partially hallucinated responses of all evaluated LLMs. These results suggest that hallucination in Arabic LLMs extends beyond factual inaccuracies, encompassing challenges related to cultural understanding, linguistic reasoning, and logical consistency. We release HalluScore to support future research on improving the reliability and cultural competence of LLMs in Arabic.

Aisha Alansari, Hamzah Luqman

Department of Information and Computer Science, King Fahd University of Petroleum and Minerals · SDAIA-KFUPM Joint Research Center for Artificial Intelligence

Multilingual Language Model Evaluation LLM Evaluation Arabic NLP Hallucination in Language Models LLM Hallucination Detection

May 16, 2026cs.CL

PaliBench: A Multi-Reference Blueprint for Classical Language Translation Benchmarks

Digital humanities projects increasingly rely on machine translation and large language models to widen access to classical, religious, and otherwise under-translated textual traditions. Yet standard translation benchmarks are poorly suited to such materials: they typically compare a system output against a single reference translation, even though classical texts often support multiple faithful renderings that differ in terminology, register, and interpretation. This article introduces PaliBench, both a benchmark for Pali-to-English translation and a reusable method for constructing multi-reference translation benchmarks for classical languages. The Pali case study draws on passages from the Sutta Pitaka aligned with independent English translations by Bhikkhu Sujato, Bhikkhu Thanissaro, and Bhikkhu Bodhi. The workflow combines LLM-assisted alignment of independently segmented translations, automated verification against source files, passage-level quality filtering, deduplication of formulaic repetitions, and multi-metric evaluation against multiple human references. The resulting benchmark contains 1,700 passages spanning 8,389 segments and approximately 345,000 tokens. We use it to evaluate ten contemporary large language models with complementary metrics, finding strong cross-metric concordance in system rankings alongside substantial variation in reliability and semantic outlier rates. The broader contribution is methodological: PaliBench shows how existing scholarly translations can be transformed into evaluation infrastructure for interpretive textual traditions without treating any single translation as definitive. Although developed for Pali Buddhist texts, the approach could be portable to other classical corpora where sufficient independent reference translations exist.

Máté Metzger, Nadnapang Phophichit

Independent Researcher · International Buddhist Studies College · Mahachulalongkornrajavidyalaya University

LLM Evaluation Machine Translation MT Evaluation

May 16, 2026cs.CL

GPF-LiveNews: A Streaming Evaluation Protocol for Group-Conditioned Framing in Large Language Models

Deployed language models are evaluated in a non-stationary environment: model versions, retrieval layers, safety systems, and real-world inputs all change over time. Static bias benchmarks remain useful, but they do not show how models frame newly emerging events for different prompted audiences. We introduce GPF-LIVENEWS, a streaming evaluation protocol and benchmark snapshot for auditing group-conditioned framing in open-ended LLM outputs. The protocol expands fresh BBC/Reuters news anchors across 42 identity labels and seven prompt families, then evaluates response bundles using semantic-sensitivity and sentiment-disparity signals. In a pilot over 12 monitoring runs and 23 hosted models, Policy/Action prompts produce the strongest semantic movement, while sentiment variation is flatter across dimensions and prompt families. The released artifact includes article metadata, prompt templates, instantiated prompts, model-output metadata, score tables, documentation, and reproduction scripts. We interpret all scores as observed-window audit signals for human review, not as permanent fairness rankings or direct proof of harmful bias.

Mohd Ariful Haque, Fahad Rahman, Kishor Datta Gupta +1

Clark Atlanta University · United International University

LLM Evaluation LLM Auditing Social Bias in Language Models Language Model Bias Evaluation

May 16, 2026cs.CL

Exploring Lightweight Large Language Models for Court View Generation

Criminal Court View Generation (CVG) is a critical task in Legal Artificial Intelligence (Legal AI), involving the generation of court view based on case facts. In this work, we systematically explore the capabilities of lightweight (smaller than 2B) large language models (LLMs) in CVG and their impact on charge prediction. Our study addresses four key questions: (1) how does different architecture of LLMs affect the CVG quality and charge prediction. (2) how does LLMs size contribute to the performance, (3) how do lightweight LLMs compare with Deep Neural Networks (DNNs) in these tasks, and (4) how does predicting charge by court view generation first compare with predicting it directly. Additionally, we also develop CVGEvalKit, an evaluation framework including three public available datasets for CVG tasks, as well as predicting their charges. Comprehensive experiments are conducted on this framework, where models are trained on a mixed training set and evaluated on each dataset's test set. Experimental results provide new insights into the trade-offs between model architecture, model size, and the influence between different tasks, highlighting the potential of lightweight LLMs in judicial AI applications. The source code is anonymously available at https://github.com/ZhitianHou/CVGEvalKit

Zhitian Hou, Tianyong Hao, Nanli Zeng +2

School of Computer Science and Engineering, Sun Yat-sen University · School of Computer Science, South China Normal University · 3China Mobile Internet Co., Ltd.

LLM Evaluation Small Language Models

May 15, 2026cs.AI

LinAlg-Bench: A Forensic Benchmark Revealing Structural Failure Modes in LLM Mathematical Reasoning

We introduce LinAlg-Bench, a diagnostic benchmark evaluating 10 frontier large language models on structured linear algebra computation across a strict dimensional gradient of 3x3, 4x4, and 5x5 matrices. Spanning 9 task types and 660 SymPy-certified problems, the benchmark exhaustively evaluates 6,600 model outputs. Beyond binary accuracy, LinAlg-Bench introduces a three-stage automated forensic pipeline classifying 1,156 failures into ten primary error tags with fine-grained subtypes, revealing that LLM mathematical failure is not random but structurally constrained by algorithm type and matrix dimension. Our central finding is a sharp behavioral threshold at 4x4 scale: below it, models fail through execution errors -- sign tracking failures, arithmetic drift, and parity errors; above it, failure transitions to computational abandonment, with models fabricating responses through tool roleplay, constraint-consistent confabulation, and structured hallucination rather than attempting computation. This fabrication-to-abandonment transition is near-universal across all model tiers and architectures, suggesting a working memory limit rather than a knowledge gap, supported by three scale-emergent error types absent at 3x3 but present at 4x4 and 5x5. We further show that solution strategy rigidity is a near-perfect predictor of 5x5 determinant accuracy, document constraint-aware confabulation as a novel structured hallucination failure mode, and release all data, model outputs, error labels, and judge pipeline publicly.

Shradha Agarwal, Deepak Rajbhar, Tariq J

Department of Nuclear Engineering and Computer Science Missouri University of Science and Technology Rolla, Missouri

Mathematical Reasoning Benchmarks LLM Evaluation Hallucination in Language Models Mathematical Reasoning LLM Mathematical Reasoning

May 15, 2026cs.CL

SKG-Eval: Stateful Evaluation of Multi-Turn Dialogue via Incremental Semantic Knowledge Graphs

Evaluating multi-turn dialogue systems remains challenging because response quality depends not only on the current prompt, but also on previously established entities, claims, and conversational commitments. Existing automatic evaluators, including LLM-as-a-judge frameworks and embedding-based metrics, largely rely on flat or turn-isolated representations, making them less effective at detecting long-range issues such as contradiction, topic drift, and entity inconsistency. To address this, we propose SKG-Eval, a quasi-deterministic and interpretable framework that models dialogue as an evolving Semantic Knowledge Graph (SKG) of entities, relations, and commitments across turns. The framework incrementally updates the graph through structured triple extraction and computes three complementary signals: (i) local relevance, measuring alignment with the current prompt and optional reference; (ii) historical consistency, evaluating how newly introduced information connects to prior conversational context using graph-based and embedding-driven signals; and (iii) logical coherence, assessed by a geometric contradiction engine that detects cross-turn conflicts without relying on NLI models or LLM judges. These signals are adaptively fused and aggregated into a length-invariant session score via recency-weighted trend analysis. Across multiple benchmarks, SKG-Eval achieves higher correlation with human judgments and substantially improves detection of long-range inconsistencies in extended conversations. In addition, the framework produces explicit contradiction certificates and deterministic scores for fixed inputs, enabling reproducible and auditable evaluation. Overall, our results suggest that structured externalized state tracking through semantic knowledge graphs provides a scalable alternative to implicit reasoning in LLM-based dialogue evaluators.

Avijit Shil, Suman Samui

Maulana Abul Kalam Azad University of Technology, West Bengal, India · National Institute of Technology Durgapur, West Bengal, India

LLM Evaluation Factual Consistency Evaluation Multi-Turn Dialogue Evaluation Automated Evaluation Knowledge Graphs

May 15, 2026cs.LG

A Unified Perturbation Framework for Analyzing Leaderboard Stability and Manipulation

Evaluation leaderboards such as LMArena play a central role in benchmarking large language models by aggregating pairwise human preferences into model rankings, yet the robustness of these rankings remains poorly understood. We present a unified perturbation framework for analyzing Bradley-Terry leaderboards under structured data modifications using influence-based approximations. Our framework studies three match-level perturbations -- Drop, Add, and Flip -- together with player removal, and evaluates their effects on top-k membership, global ranking consistency via Kendall's tau, and confidence-interval-based uncertainty. Across Chatbot Arena and six additional pairwise-comparison datasets, we show that modern leaderboards are non-robust across all three objectives: sub-1% targeted perturbations can change the top-ranked model, degrade Kendall's tau, and alter confidence intervals. Beyond robustness auditing, we show that the same influence scores enable efficient targeted perturbations, promoting or demoting specific models and reducing target-model uncertainty with fewer actions than previous manipulation and active-sampling baselines. By summarizing these effects with normalized dataset-level robustness scores, our framework provides a practical and helpful tool for auditing leaderboard stability and motivating more robust evaluation protocols.

Hosna Oyarhoseini, Jimmy Lin, Amir-Hossein Karimi

University of Waterloo, Waterloo, Ontario, Canada.

LLM Evaluation Learning to Rank LLM Auditing Pairwise Ranking Bradley–Terry Model

May 15, 2026cs.AI

Can We Trust AI-Inferred User States. A Psychometric Framework for Validating the Reliability of Users States Classification by LLMs in Operational Environments

The use of large language models to assess user states in conversational and adaptive systems is based on the assumption that the metrics used for such assessment are stable and interpretable at the level of individual scores. This paper empirically tests this assumption, focusing on the psychometric reliability of artificial intelligence (AI) measures of user states. This study employed replication evaluation procedures to assess the repeatability of a broad set of metrics across three different bimodal large language models (GPT-4o audio, Gemini 2.0 Flash, Gemini 2.5 Flash). Analyses include both individual score reliability and aggregated reliability, allowing us to distinguish metrics potentially useful for real-time adaptation from those that retain their value only in aggregated analyses. The results demonstrate that metric reliability cannot be considered a default property in interpretive domains. The lack of stability at the level of individual scores precludes the interpretation of such scores as indicators of user state in real-time adaptive systems, even if these metrics demonstrate stability after aggregation. At the same time, the study indicates that individually unstable metrics can retain analytical utility in post-hoc studies, identifying rules governing interactions and their relationships with user experience parameters such as satisfaction, trust, and engagement. The main contribution of this work, besides quantifying the severity of the problem (only 31 of 213 metrics met the criteria), is the proposal of a replicable evaluation framework, enabling measurable evaluations of metric applicability. This approach supports more responsible AI design of adaptive systems, in which the interpretation of results requires explicit validation of reliability and monitoring for violations over time.

Izabella Krzeminska, Michal Butkiewicz, Ewa Komkowska

Orange Research, AI Center, Warsaw, Poland

LLM Evaluation Psychometric Validation LLM Reliability

May 15, 2026cs.CL

Evaluating Chinese Ambiguity Understanding in Large Language Models

Linguistic ambiguity is critical to the robustness of Large Language Models (LLMs), yet existing research focuses mostly on English, with limited attention devoted to Chinese. Existing Chinese ambiguity datasets (e.g., CHAmbi) suffer from poor scalability. Guided by Potential Ambiguity (PA) Theory, we design a semi-automatic pipeline to construct CHA-Gen. It is the first PA Theory-grounded Chinese ambiguity dataset, which comprises 5,712 sentences (2,414 ambiguous, 3,298 unambiguous) across 18 potential ambiguous structures. Evaluating LLMs (e.g. Gemma 3, Qwen 2.5/3 series) via direct querying and machine translation, we find that LLMs struggle with ambiguity detection (improved by CoT prompting). Analysis of Qwen3-32B's CoT rationales reveals three common failure modes: ambiguity blindness, misattribution, and premature resolution. Uncertainty quantification with semantic entropy metric shows higher uncertainty for ambiguous sentences. Moreover, instruction tuning induces overconfidence, whereas Base models better capture semantic diversity. We further observe that models exhibit a bias toward dominant interpretations. Our work provides a scalable approach for Chinese ambiguity corpus and insights into LLMs' ambiguity handling, laying a foundation for enhancing Chinese ambiguity research in LLMs.

Junwen Mo, Yuanzhi Lu, Yifang Xue +2

Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan · School of Software Engineering, South China University of Technology, Guangzhou Higher Education Mega Centre, Panyu District, Guangzhou, 510006, Guangdong, China

May 15, 2026cs.CL

MHGraphBench: Knowledge Graph-Grounded Benchmarking of Mental Health Knowledge in Large Language Models

Large language models (LLMs) are increasingly used in the mental health domain, yet it remains unclear how well they capture related biomedical knowledge and how reliably they apply it to clinically salient structured judgments. Here, we present a knowledge-graph (KG)-grounded benchmark for assessing LLMs on mental-health entity recognition, relation judgment, and two-hop reasoning. The benchmark is derived from PrimeKG and comprises nine task families with KG-supported answers and controlled negative options. Experiments across 15 closed- and open-source LLMs reveal a persistent recognition-to-judgment gap: leading models achieve near-ceiling performance on entity typing and on the small relation-typing subset, yet they still struggle with relation prediction and two-hop reasoning. Additionally, short KG-derived snippets benefit some models but degrade performance for others. Moreover, output-format reliability can substantially influence measured performance under constrained multiple-choice settings, highlighting the critical role of response validity in benchmark-based evaluation. MHGraphBench should therefore be interpreted as evaluating agreement with a curated mental-health slice of PrimeKG under a constrained multiple-choice interface, rather than as a direct assessment of real-world clinical safety.

Weixin Liu, Congning Ni, Shelagh A. Mulvaney +4

Vanderbilt University, Nashville, TN, USA · Vanderbilt University Medical Center, Nashville, TN, USA · Virginia Tech, Blacksburg, VA, USA

LLM Evaluation Healthcare Mental Health Clinical Language Model Evaluation Knowledge Graphs LLM Reasoning+1

May 15, 2026cs.AI

RTL-BenchMT: Dynamic Maintenance of RTL Generation Benchmark Through Agent-Assisted Analysis and Revision

This paper introduces RTL-BenchMT, an agentic framework for dynamically maintaining RTL generation benchmarks. Large Language Models (LLMs) assisted automated RTL generation is one of the most important directions in EDA research. However, current RTL benchmarks face two critical challenges: (1) flawed cases in the benchmarks and (2) overfitting to the benchmarks. Both challenges are difficult to resolve purely by manual engineering effort. To address these issues and systematically reduce human maintenance costs, we propose an automated agentic framework, RTL-BenchMT. RTL-BenchMT focuses on two key applications: (1) automatically identifying and revising flawed benchmark cases and (2) automatically detecting and updating overfitting cases. With the assistance of RTL-BenchMT, we conduct a thorough, in-depth analysis of flawed and overfitting cases and produce a refined benchmark suite that will be open-sourced to the community.

Jing Wang, Shang Liu, Hangan Zhou +1

Hong Kong University of Science and Technology · Clear Water Bay, Hong Kong

LLM Evaluation Electronic Design Automation Code Generation RTL Code Generation

May 14, 2026cs.CL

FINESSE-Bench: A Hierarchical Benchmark Suite for Financial Domain Knowledge and Technical Analysis in Large Language Models

Large language models (LLMs) are increasingly being applied to financial analysis, reporting, investment decision support, risk management, compliance, and professional training. However, robust evaluation of their domain competence in finance remains incomplete. Widely used open benchmarks such as FinQA, ConvFinQA, and TAT-QA have played an important role in advancing financial question answering and numerical reasoning, but they focus primarily on question answering over financial reports and do not provide an explicit hierarchy of professional difficulty. Broader resources, including FinanceBench, PIXIU, FinBen, and FLaME, expand the coverage of financial tasks, yet the problem of evaluating the transition from foundational knowledge to expert-level financial reasoning remains open. In this work, we present FINESSE-Bench, a suite of eight specialized benchmarks comprising 3,993 questions for hierarchical evaluation of financial competencies in LLMs. FINESSE-Bench combines exam-oriented datasets inspired by professional certifications (CFA-like Levels 1-3, CMT-like Level 2, and CFTe-like Level 1), applied trading task collections, and a Russian-language olympiad benchmark. This design enables evaluation of domain breadth, performance degradation as difficulty increases, the ability to solve computational tasks, and model behavior in specialized financial domains. We also describe a unified evaluation protocol covering multiple-choice questions, numerical answers, and short open-ended responses, together with an automated scoring scheme for freeform answers based on the LLM-as-judge paradigm. FINESSE-Bench is intended both as a complement to existing open financial benchmarks and as a tool for more substantive evaluation of professionally relevant financial competencies in large language models.

Dmitry Stanishevskii, Nini Kamkia, Alexey Khoroshilov +4

Lime FinTech

LLM Evaluation Quantitative Finance Benchmark Design Finance

May 14, 2026cs.CL

Neural Activation Patterns Across Language Model Architectures: A Comprehensive Analysis of Cognitive Task Performance

This paper presents a comprehensive analysis of neural activation patterns across six distinct large language model (LLM) architectures, examining their performance on twelve cognitive task categories. Through systematic measurement of final activation values, attention entropy, and sparsity patterns, we reveal fundamental differences in how encoder and decoder architectures process diverse cognitive tasks. Our analysis of 144 task-model combinations demonstrates that mathematical reasoning consistently produces the highest attention entropy across all architectures, while decoder models exhibit significantly higher sparsity patterns compared to encoder models. The findings provide critical insights into the computational characteristics of modern language models and their task-specific neural behaviors, with implications for model selection and optimization in big data applications.

Mahdi Naser-Moghadasi, Faezeh Ghaderi

Research Division, BrightMind AI, Seattle, WA · Texas Tech University, Lubbock, TX · University of Texas at Arlington

LLM Evaluation Decoder-Only Language Models LLM Interpretability

May 14, 2026cs.LG

Margin-Adaptive Confidence Ranking for Reliable LLM Judgement

Jung et al. (2025) introduce a hypothesis testing framework for guaranteeing agreement between large language models (LLMs) and human judgments, relying on the assumption that the model's estimated confidence is monotonic with respect to human-disagreement risk. In practice, however, this assumption may be violated, and the generalization behavior of the confidence estimator is not explicitly analyzed. We mitigate these issues by learning a dedicated confidence estimator instead of relying on heuristic confidence signals. Our approach leverages simulated annotator diversity and a margin-based ranking formulation to explicitly model how confidently an LLM distinguishes between human-agreement and human-disagreement cases. We further derive generalization guarantees for this estimator, revealing a margin-dependent trade-off that informs the design of an adaptive estimator training procedure. When integrated into fixed-sequence testing, the learned confidence estimator yields improved ranking accuracy and empirically strengthens the monotonic relationship between confidence and disagreement risk, leading to higher success rates in satisfying target agreement levels across multiple datasets and judge models.

Gaojie Jin, Yong Tao, Lijia Yu +1

Department of Computer Science, University of Exeter · Institute of AI for Industries, Chinese Academy of Sciences · Department of Mathematics and Computer Science, Eindhoven University of Technology

LLM Evaluation LLM-as-a-Judge Learning to Rank Confidence Estimation in Language Models Human-AI Agreement LLM Uncertainty Estimation

May 14, 2026cs.LG

LPDS: Evaluating LLM Robustness Through Logic-Preserving Difficulty Scaling

As large language models (LLMs) are increasingly deployed to perform tasks with minimal human oversight, it is crucial that these models operate robustly. In particular, a model that can solve a given problem should not fail simply because certain entities

\unicode{x2013}

such as names, numbers, or other contextual details

\unicode{x2013}

have changed while the underlying problem logic remains the same. Prior work suggests that current LLMs still struggle with this form of robustness: they often succeed on some variations of a problem but fail on others. However, existing evaluations often lack a systematic way to identify which logic-preserving variations are most likely to induce failure. Instead, they typically test a random subset of allowable variations, which can overstate robustness. To address this gap, we introduce logic-preserving difficulty scaling (LPDS), a framework that (i) quantifies the difficulty of a problem variation and (ii) systematically searches the space of allowable variations to find those that maximize difficulty and expose failures. We show that as difficulty increases, performance declines and errors in the models' reasoning chains become more pronounced. We further demonstrate that LPDS efficiently finds difficult problem variations for a model, resulting in performance drops up to 5 times larger compared to random sampling. Finally, we show that fine-tuning on more difficult variations leads to more consistent robustness gains than training on easier ones.

Philipp Mondorf, Samuel J. Bell, Jesse Dodge +1

FAIR at Meta · LMU Munich · Munich Center for Machine Learning +1

LLM Evaluation Neural Network Robustness LLM Reliability Language Model Robustness

May 14, 2026cs.LG

Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory

Memory plays a central role in enabling large language models (LLMs) to operate over sequential tasks by accumulating and reusing experience over time. However, existing evaluations of LLM memory mostly rely on aggregate metrics such as final hold-out accuracy or cumulative online performance, which can obscure critical failure modes such as forgetting and negative transfer. In this paper, we introduce SeqMem-Eval, a diagnostic evaluation framework for sequentially evolving LLM memory. Drawing inspiration from continual learning, it targets a test-time setting in which memory is external, prompt-mediated, and updated without modifying model parameters. Rather than focusing only on final performance, SeqMem-Eval evaluates how memory states evolve, generalize, consolidate experience, and retain useful information during sequential inference. Specifically, it measures online utility, hold-out generalization, backward transfer, and forgetting, providing a finer-grained view of memory quality. Through extensive experiments across diverse tasks and memory methods, we show that higher final or cumulative accuracy does not necessarily imply better memory quality: many methods exhibit strong performance gains while suffering from substantial forgetting or negative transfer. Moreover, different memory designs exhibit distinct trade-offs between adaptability and stability that remain invisible under standard evaluation metrics.

Songwei Dong, Zihan Chen, Chengshuai Shi +3

University of Virginia · Princeton University

Continual Learning for LLMs LLM Evaluation Memory-Augmented Language Models Persistent Memory for Language Models LLM Memory Catastrophic Forgetting

May 14, 2026cs.LG

LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design

LLMs are increasingly deployed in autonomous laboratories, under the assumption that their domain priors and reasoning over iterative feedback let them converge on good designs in fewer iterations than feedback-only baselines. Current iterative scientific design benchmarks, however, score only outcome snapshots at fixed horizons. This leaves the learning trajectory unmeasured, even though the trajectory is what captures learning efficiency, where each iteration saved is a real saving in cost and time. Motivated by this, we examine three evaluation choices that change the conclusions one draws about LLM learning efficiency in iterative scientific design: what to measure, what baseline to compare against, and what to ground against. We introduce LEAPBench, Learning Efficiency in Adaptive Processes, a 55-task framework that pairs a best-so-far area under the curve (AUC) trajectory metric with a classical Bayesian-optimization reference and an audit grounded in published literature. Applied to eight contemporary LLMs, switching from final-outcome to trajectory scoring changes the best-model decision on 53% of tasks at matched horizons, and exposes efficiency gains overlooked by outcome-based scoring. LLMs do not outperform a classical Bayesian baseline. On 16 biology tasks where the oracle's reward signal is aligned with configurations from the published-best design, domain-aware prompting leads to LLM choices that match the published-best's approximately 10 percentage points less often than domain-agnostic prompting at iteration 30. The pattern is sharpest on 6 tasks where the literature-typical and published-best configurations diverge, and domain-agnostic prompting matches the published-best more often on all 6. The trajectory metric also doubles as a tractable training target. Offline reinforcement learning with the metric as a reward improves performance on 14 of 21 held-out tasks.

Marilyn Zhang, Tianfeng Chen, Fabián Barzuna +2

LLM Evaluation AI Agent Benchmarks Automated Evaluation Autonomous Experimentation

May 14, 2026cs.AI

Zero-Shot Goal Recognition with Large Language Models

Large language models have recently reached near-parity with classical planners on well-known planning domains, yet this competence relies on world-knowledge exploitation rather than genuine symbolic reasoning. Goal recognition is a complementary abductive task structurally better suited to LLM strengths: it consists of evaluating consistency with world knowledge rather than generating novel action sequences. This paper provides the first systematic zero-shot evaluation of frontier LLMs as goal recognisers on key classical PDDL benchmarks. Our results show that LLM competence on goal recognition is uneven: some models scale with evidence and approach landmark-based accuracy at full observations, while others remain anchored to world-knowledge priors regardless of how much evidence accumulates. Qualitative analysis of model reasoning traces reveals that this divergence reflects a fundamental difference in evidence integration rather than domain familiarity. These findings position goal recognition as a principled benchmark for the foundational planning knowledge of LLMs.

Kin Max Piamolini Gusmão, Nathan Gavenski, Nir Oren +1

PUCRS · King’s College London · University of Aberdeen +1

Zero-Shot Learning LLM Evaluation Symbolic Planning

May 14, 2026cs.AI

Small, Private Language Models as Teammates for Educational Assessment Design

Generative AI increasingly supports educational design tasks, e.g., through Large Language Models (LLMs), demonstrating the capability to design assessment questions that are aligned with pedagogical frameworks (e.g., Bloom's taxonomy). However, they often rely on subjective or limited evaluation methods; focus primarily on proprietary models; or rarely systematically examine generation, evaluation, or deployment constraints in real educational settings. Meanwhile, Small Language Models (SLMs) have emerged as local alternatives that better address privacy and resource limitations; yet their effectiveness for assessment tasks remains underexplored. To address this gap, we systematically compare LLMs and SLMs for assessment question design; evaluate generation quality across Bloom's taxonomy levels using reproducible, pedagogically grounded metrics; and further assess model-based judging against expert-informed evaluation by analyzing reliability and agreement patterns. Results show that SLMs achieve competitive performance across key pedagogically motivated quality dimensions while enabling local, privacy-sensitive deployment. However, model-based evaluations also exhibit systematic inconsistencies and bias relative to expert ratings. These findings provide evidence to posit language models as bounded assistants in assessment workflows; underscore the necessity of Human-in-the-Loop; and advance the automated educational question generation field by examining quality, reliability, and deployment-aware trade-offs.

Chris Davis Jaldi, Anmol Saini, Shan Zhang +3

Wright State University, USA · University of Florida, USA · TIB – Leibniz Information Centre for Science and Technology, Germany

LLM Evaluation LLM-as-a-Judge Educational Assessment Small Language Models Generative AI in Education

May 14, 2026cs.AI

XDomainBench: Diagnosing Reasoning Collapse in High-Dimensional Scientific Knowledge Composition

Large Language Models (LLMs) are increasingly deployed for knowledge synthesis, yet their capacity for compositional generalization in scientific knowledge remains under-characterized. Existing benchmarks primarily focus on single-turn restricted scenarios, failing to capture the capability boundaries exposed by real-world interactive scientific workflows. To address this, we introduce XDomainBench, a diagnostic benchmark for interactive interdisciplinary scientific reasoning. We formalize the composition order and mixture structure to enable systematic stress-testing from single-discipline to inter-disciplinary, comprising 8,598 interactive sessions across 20 domains and 4 task categories, with 8 realistic trajectory patterns covering difficulty and domain-mixture dynamics, simulating real AI4S scenarios. Large-scale evaluation of LLMs reveals a systematic reasoning collapse as composition order increases, stemming from two root causes: (i) direct difficulty increases induced by domain composition, and (ii) indirect interaction-amplified failures where trajectory patterns trigger error accumulation, reasoning breaks, and domain confusion, ultimately leading to session collapse.

Gong Zhiren, Tiantong Wu, Jiaming Zhang +9

College of Computing and Data Science, Nanyang Technological University, Singapore · Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore · Department of Mathematics and Mathematical Statistics, Umeå University, Sweden +2

AI for Science LLM Evaluation Scientific Reasoning AI Agent Benchmarks Compositional Generalization

May 14, 2026cs.CL

Dimension-Level Intent Fidelity Evaluation for Large Language Models: Evidence from Structured Prompt Ablation

Holistic evaluation scores capture overall output quality but do not distinguish whether a model reproduced the structural form of a user's request from whether it preserved the user's specific intent. We propose a dimension-level intent fidelity evaluation framework, applied here through a structured prompt ablation study across 2,880 outputs spanning three languages, three task domains, and six LLMs, that separately measures structural recovery and intent fidelity for each semantic dimension. This framework reveals a systematic structural-fidelity split: among Chinese-language outputs with complete paired scores, 25.7% received perfect holistic alignment scores (GA=5) while exhibiting measurable dimensional intent deficits; among English-language outputs, this proportion rose to 58.6%. Human evaluation confirmed that these split-zone outputs represent genuine quality deficits and that dimensional fidelity scores track human judgements more reliably than holistic scores do. A public-private decomposition of 2,520 ablation cells characterises when models successfully compensate for missing intent and when they fail, while proxy annotation distinguishes prior inferability from default recoverability. A weight-perturbation experiment shows that moderate misalignment is typically absorbed, whereas severe dimensional inversion is consistently harmful. These findings demonstrate that dimension-level intent fidelity evaluation is a necessary complement to holistic assessment when evaluating LLM outputs for user-specific tasks.

GAng Peng

Huizhou Lateni AI Technology Co., Ltd., Huizhou, China · Huizhou University, Huizhou, China

Multilingual Language Model Evaluation LLM Evaluation Language Model Generation Evaluation Instruction Following

May 14, 2026cs.AI

Deepchecks: Evaluating Retrieval-Augmented Generation (RAG)

Large Language Models (LLMs) augmented with Retrieval-Augmented Generation (RAG) techniques are revolutionizing applications across multiple domains, such as healthcare, finance, and customer service. Despite their potential, evaluating RAG systems remains a complex challenge due to the stochastic nature of generated outputs and the intricate interplay between retrieval and generation components. This paper introduces Deepchecks, a comprehensive framework tailored for evaluating RAG applications. Deepchecks' evaluation framework addresses RAG applications evaluation through a multi-faceted approach, root cause analysis and production monitoring. By ensuring alignment with application-specific requirements, Deepchecks framework provides a robust foundation for assessing reliability, relevance, and user satisfaction in RAG systems.

Assaf Gerner, Netta Madvil, Nadav Barak +11

Deepchecks, Ramat Gan, Israel · Ben-Gurion University, Beer Sheva, Israel

LLM Evaluation RAG Evaluation Automated Evaluation

May 14, 2026cs.CR

The Great Pretender: A Stochasticity Problem in LLM Jailbreak

"Oh-Oh, yes, I'm the great pretender. Pretending that I'm doing well. My need is such, I pretend too much..." summarizes the state in the area of jailbreak creation and evaluation. You find this method to generate adversarial attacks proposed by a reputable institution (e.g., BoN from Anthropic or Crescendo from Microsoft Research). However, this method does not deliver on the promise claimed in the paper despite having top ASR scores against industry-grade LLMs. You successfully generate the jailbreak prompts against your target (open) model. However, the generated jailbreak prompt works against the target model with a 50% consecutive success rate (5 out of 10 attempts) despite having an 80% ASR (on paper) on the latest closed-source model (with a guardrail system)! This observation leads us to think. First, Attack Success Rate (ASR), the primary metric for LLM jailbreak benchmarking, is not a stable quantity. Second, published ASR numbers are therefore systematically inflated and incomparable across papers. Therefore, we wonder "Why a successful jailbreak prompt does not perform consistently well against a target model on which the prompts have been optimized?". To answer this question, we study the impact of stochasticity not only during attack evaluation but also during attack generation. Our evaluation includes several jailbreak attacks, models (different sizes and providers), and judges. In addition, we propose a new metric and two new frameworks (CAS-eval and CAS-gen). Our evaluation framework, CAS-eval, shows that an attack can have an ASR drop of up to 30 percentage points when a jailbreak prompt needs to succeed on more than one attempt. Thankfully, our attack generation framework (CAS-gen) improves previous jailbreak methods and helps them recover this loss of 30 percentage points!

Jean-Philippe Monteuuis, Cong Chen, Jonathan Petit

Qualcomm Technologies, Inc.

LLM Safety Benchmarks LLM Evaluation Adversarial Prompt Generation LLM Jailbreak Attacks LLM Safety Evaluation Benchmark Validity+1

May 13, 2026cs.AI

Unsteady Metrics and Benchmarking Cultures of AI Model Builders

The primary way to establish and compare competencies in foundation and generative AI models has shifted from peer-reviewed literature to press releases and company blog posts, where model builders highlight results on selected benchmarks. These artifacts now largely define the state of the art for researchers and the public. Despite their prominence, which benchmarks model builders choose to highlight, and what they communicate through this selection, is underexamined. To investigate, we introduce and open-source Benchmarking-Cultures-25, a dataset of 231 benchmarks highlighted across 139 model releases in 2025 from 11 major AI builders, alongside an interactive tool to explore the data. Our analysis reveals a fragmented evaluation landscape with limited cross-model comparability: 63.2% of highlighted benchmarks are used by a single builder, and 38.5% appear in just one release. Few achieve widespread use (e.g., GPQA Diamond, LiveCodeBench, AIME 2025). Moreover, benchmarks are attributed different competencies by different builders, depending on their narrative. To disentangle these conflicting presentations, we develop a unified taxonomy mapping diverging terminology to a shared framework of measured signals based on what benchmark authors claim to measure. "General knowledge application" is the second most popular, yet vaguely defined, category. Qualitative analysis shows many such benchmarks deemphasize construct validity, instead framing results as indicators of progress toward AGI. Their authors claim to measure knowledge or reasoning broadly, yet mostly evaluate STEM subjects (especially math). We argue that highlighted benchmarks function less as standardized measurement tools and more as flexible narrative devices prioritizing market positioning over scientific evaluation. Data: https://hf.co/datasets/matybohacek/benchmarking-cultures-25; tool: https://bench-cultures.net.

Stefan Baack, Christo Buschek, Maty Bohacek

Independent Researcher · Mozilla Fellowship · Stanford University

LLM Evaluation Benchmark Design Benchmark Validity Generative AI Evaluation

May 13, 2026q-bio.NC

Do Language Models Align with Brains? Prediction Scores Are Not Enough

Brain-language model comparisons often interpret neural prediction scores as evidence that model representations capture brain-relevant language computation. We asked whether language models align with brains, and whether prediction scores are enough to support that claim, using L-PACT, a source-audited framework that evaluates predictive, relational, mechanism-stripping, and reliability-bounded evidence. Across primary naturalistic language neural datasets and derived language-model representations, L-PACT compared real model features with nuisance baselines and severe controls, tested whether model-to-brain profiles reproduced brain-to-brain patterns, recomputed held-out scores after mechanism stripping, and normalized evidence against brain-brain ceilings. The locked analysis set contains 414 predictive-control rows, 2304 relational profile rows, 4320 mechanism-stripping rows, 420 brain-brain ceiling rows, and 146 integrated decision rows. Assay-sensitivity checks showed that brain-brain reliability, brain-as-model run-to-run relational profiles, independent low-level neural and WAV-derived acoustic-envelope gates, and a deterministic implanted-signal simulation can produce positive evidence when expected. Nevertheless, no real model row passed the predictive, relational, mechanism-stripping, or operational Turing-bounded reliability gates; all 146 integrated rows were control-explained. Less stringent single-criterion rules would have counted raw positive predictive, relational, stripping-delta, and ceiling-normalized effects, but L-PACT downgraded them because controls explained the apparent evidence. In the analyzed derived artifact set, the tested language-model representations do not satisfy L-PACT alignment gates; apparent positives are converted into an auditable control-explained taxonomy rather than treated as structural alignment.

Xiao Jia

School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen, China

May 13, 2026cs.LG

Improving Reproducibility in Evaluation through Multi-Level Annotator Modeling

As generative AI models such as large language models (LLMs) become more pervasive, ensuring the safety, robustness, and overall trustworthiness of these systems is paramount. However, AI is currently facing a reproducibility crisis driven by unreliable evaluations and unrepeatable experimental results. While human raters are often used to assess models for utility and safety, they introduce divergent biases and subjective opinions into their annotations. Overcoming this variance is exceptionally challenging because very little data exists to study how experimental repeatability actually improves as the annotator pool grows. Standard evaluation practices typically rely on a small number of annotations per item (often 3 to 5) and lack the persistent rater identifiers necessary to model individual variance across items. In this work, we introduce a multi-level bootstrapping approach to realistically model annotator behavior. Leveraging datasets with a large number of ratings and persistent rater identifiers, we analyze the tradeoffs between the number of items (

N

) and the number of responses per item (

K

) required to achieve statistical significance.

Deepak Pandita, Flip Korn, Chris Welty +1

Rochester Institute of Technology · Google Research

Inter-Rater Reliability LLM Evaluation Human-in-the-Loop Evaluation ML Reproducibility

May 13, 2026cs.SE

(How) Do Large Language Models Understand High-Level Message Sequence Charts?

Large Language Models (LLMs) are being employed widely to automate tasks across the software development life-cycle. It is, however, unclear whether these tasks are performed consistently with respect to the semantics of the artefacts being handled. This question is particularly under-researched concerning architectural design specification. In this paper, we address this question for High-Level Message Sequence Charts (HMSCs). These are visual models with a rigorous formal semantics that have been used for various purposes, including as a foundation for Sequence Diagrams in the Unified Modelling Language (UML). We examine whether LLMs "understand" the semantics of HMSCs by examining three LLMs (Gemini-3, GPT-5.4, and Qwen-3.6) on how they perform 129 semantic tasks ranging from querying basic semantic constructs in HMSCs (i.e., events and their ordering) to semantic-preserving abstractions and compositions, and calculating the set of traces and trace-equivalent labelled transition systems. The results show that LLMs only have a modest understanding of the formal semantics of HMSCs (ca. 52% overall accuracy), with great variability across different semantic concepts: while LLMs seem to understand the basic semantic concepts of MSCs (ca. 88% accuracy), they struggle with semantic reasoning in tasks involving abstraction and composition (ca. 36% accuracy) and traces and LTSs (ca. 42% accuracy). In particular, all three LLMs struggle with the notions of co-region and explicit causal dependencies and never employed them in semantic-preserving transformations.

Mohammad Reza Mousavi

Department of Informatics, King’s College London

LLM Evaluation Chart Understanding LLM Reasoning

May 13, 2026cs.CL

RTLC -- Research, Teach-to-Learn, Critique: A three-stage prompting paradigm inspired by the Feynman Learning Technique that lifts LLM-as-judge accuracy on JudgeBench with no fine-tuning

LLM-as-a-judge is now the default measurement instrument for open-ended generation, but on the public JudgeBench benchmark even strong instruction-tuned judges barely scrape past random on objective-correctness pairwise items. We introduce RTLC, a three-stage prompting recipe -- Research, Teach-to-Learn, Critique -- that promotes a single black-box LLM into an ensemble-of-thought judge with no fine-tuning, retrieval, or external tools. Stage 1 wraps the input in a fixed pedagogical scaffold porting the Feynman Learning Technique (study

\to

teach

\to

find gaps

\to

simplify) into LLM prompting. Stage 2 draws N=10 independent candidate verdicts at temperature 0.4. Stage 3 acts as its own critic, cross-comparing the candidate set against the original question to emit one critiqued verdict at temperature 0. On JudgeBench-GPT (350 hard pairwise items), Claude 3.7 Sonnet's pairwise accuracy climbs from 64.6% (single-shot vanilla prompt) to 78.6% (RTLC critique-of-10) -- an absolute 14.0-percentage-point gain. RTLC also beats N=10 self-consistency majority voting (77.7%) and a zero-shot first candidate (74.0%). A clean three-step ablation attributes +9.4 pp to the Teach-to-Learn scaffold, +3.7 pp to N=10 marginalisation, and +0.9 pp to explicit critique. We discuss the cost-accuracy frontier (RTLC sits above self-consistency at every working point), the error-budget breakdown across the four JudgeBench categories (knowledge, reasoning, math, coding), and how RTLC composes orthogonally with post-hoc judge-score calibration, with the two interventions compounding multiplicatively in practice.

Andrea Morandi

Cisco Systems, Inc.

LLM Evaluation Pairwise Comparison LLM-as-a-Judge Language Model Generation Evaluation