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.

Apr 25, 2026

An Empirical Evaluation of Locally Deployed LLMs for Bug Detection in Python Code

Large language models (LLMs) have demonstrated strong performance on a wide range of software engineering tasks, including code generation and analysis. However, most prior work relies on cloud-based models or specialized hardware, limiting practical applicability in privacy-sensitive or resource-constrained environments. In this paper, we present a systematic empirical evaluation of two locally deployed LLMs, LLaMA 3.2 and Mistral, for real-world Python bug detection using the BugsInPy benchmark. We evaluate 349 bugs across 17 projects using a zero-shot prompting approach at the function level and an automated keyword-based evaluation framework. Our results show that locally executed models achieve accuracy between 43% and 45%, while producing a large proportion of partially correct responses that identify problematic code regions without pinpointing the exact fix. Performance varies significantly across projects, highlighting the importance of codebase characteristics. The results demonstrate that local models can identify a meaningful share of bugs, though precise localization remains difficult for locally executed LLMs, particularly when handling complex and context dependent bugs in realistic development scenarios.

Jelena Ilić Vulićević

Independent Researcher

LLM Evaluation On-Device Language Model Inference

Apr 25, 2026

Evaluating Large Language Models on Computer Science University Exams in Data Structures

We present a comprehensive evaluation of Large Language Models (LLMs) on Computer Science (CS) Data Structure examination questions. Our work introduces a new benchmark dataset comprising exam questions from Tel Aviv University (TAU), curated to assess LLMs' abilities in handling closed and multiple-choice questions. We evaluated the performance of OpenAI's GPT 4o and Anthropic's Claude 3.5, popular LLMs, alongside two smaller LLMs, Mathstral 7B and LLaMA 3 8B, across the TAU exams benchmark. Our findings provide insight into the current capabilities of LLMs in CS education.

Edan Gabay, Yael Maoz, Jonathan Stahl +7

Blavatnik School of Computer Science and AI

LLM Evaluation Computer Science Education Multiple-Choice Question Answering Question Answering

Apr 25, 2026

Fine-tuning vs. In-context Learning in Large Language Models: A Formal Language Learning Perspective

Large language models (LLMs) operate in two fundamental learning modes - fine-tuning (FT) and in-context learning (ICL) - raising key questions about which mode yields greater language proficiency and whether they differ in their inductive biases. Prior studies comparing FT and ICL have yielded mixed and inconclusive results due to inconsistent experimental setups. To enable a rigorous comparison, we propose a formal language learning task - offering precise language boundaries, controlled string sampling, and no data contamination - and introduce a discriminative test for language proficiency, where an LLM succeeds if it assigns higher generation probability to in-language strings than to out-of-language strings. Empirically, we find that: (a) FT has greater language proficiency than ICL on in-distribution generalization, but both perform equally well on out-of-distribution generalization. (b) Their inductive biases, measured by the correlation in string generation probabilities, are similar when both modes partially learn the language but diverge at higher proficiency levels. (c) Unlike FT, ICL performance differs substantially across models of varying sizes and families and is sensitive to the token vocabulary of the language. Thus, our work demonstrates the promise of formal languages as a controlled testbed for evaluating LLMs, behaviors that are difficult to isolate in natural language datasets. Our source code is available at https://github.com/bishwamittra/formallm.

Bishwamittra Ghosh, Soumi Das, Till Speicher +5

Max Planck Institute for Software Systems, Germany · Boston University, USA

LLM Evaluation LLM Fine-Tuning In-Context Learning Language Modeling

Apr 24, 2026

Evaluating Temporal Consistency in Multi-Turn Language Models

Language models are increasingly deployed in interactive settings where users reason about facts over time rather than in isolation. In such scenarios, correct behavior requires models to maintain and update implicit temporal assumptions established earlier in a conversation. We study this challenge through the lens of temporal scope stability: the ability to preserve, override, or transfer time-scoped factual context across dialogue turns. We introduce ChronoScope, a large-scale diagnostic benchmark designed to isolate temporal scope behavior in controlled multi-turn interactions, comprising over one million deterministically generated question chains grounded in Wikidata. ChronoScope evaluates whether models can correctly retain inferred temporal scope when follow-up questions omit explicit time references, spanning implicit carryover, explicit scope switching, cross-entity transfer, and longer temporal trajectories. Through extensive evaluation of state-of-the-art language models, we find that temporal scope stability is frequently violated in controlled multi-turn settings, with models often drifting toward present-day assumptions despite correct underlying knowledge. These failures intensify with interaction length and persist even under oracle context conditions, revealing a gap between single-turn factual accuracy and coherent temporal reasoning under sequential interaction. We make our dataset and evaluation suite publicly available at https://github.com/yashkumaratri/ChronoScope

Yash Kumar Atri, Steven L. Johnson, Tom Hartvigsen

University of Virginia

LLM Evaluation Temporal Reasoning in Language Models Multi-Turn Dialogue Evaluation Language Modeling Temporal Consistency

Apr 24, 2026

A Systematic Approach for Large Language Models Debugging

Large language models (LLMs) have become central to modern AI workflows, powering applications from open-ended text generation to complex agent-based reasoning. However, debugging these models remains a persistent challenge due to their opaque and probabilistic nature and the difficulty of diagnosing errors across diverse tasks and settings. This paper introduces a systematic approach for LLM debugging that treats models as observable systems, providing structured, model-agnostic methods from issue detection to model refinement. By unifying evaluation, interpretability, and error-analysis practices, our approach enables practitioners to iteratively diagnose model weaknesses, refine prompts and model parameters, and adapt data for fine-tuning or assessment, while remaining effective in contexts where standardized benchmarks and evaluation criteria are lacking. We argue that such a structured methodology not only accelerates troubleshooting but also fosters reproducibility, transparency, and scalability in the deployment of LLM-based systems.

Basel Shbita, Anna Lisa Gentile, Bing Zhang +10

1IBM Research, San Jose, CA, USA · 2IBM Research, Bengaluru, India

Apr 24, 2026

AutoPyVerifier: Learning Compact Executable Verifiers for Large Language Model Outputs

Verification is becoming central to both reinforcement-learning-based training and inference-time control of large language models (LLMs). Yet current verifiers face a fundamental trade-off: LLM-based verifiers are expressive but hard to control and prone to error, while deterministic executable verifiers are reliable and interpretable but often limited in capability. We study the following question: given a development set of LLM outputs and labels for a target objective, such as correctness, can we automatically induce a minimal set of Python verifiers whose joint satisfaction closely matches that objective? We propose AutoPyVerifier, a framework that uses an LLM to synthesize candidate verifier functions and then refines them through search over a directed acyclic graph (DAG). By navigating the DAG, AutoPyVerifier systematically explores the space of deterministic executable verifiers and selects a compact verifier set whose joint satisfaction best approximates the target objective. Across mathematical reasoning, coding, function calling, and instruction-following benchmarks for several state-of-the-art LLMs, AutoPyVerifier improves target-objective prediction by up to 55.0 F1 points over the initial LLM-generated verifier sets. Additional analyses show that the most useful verification targets vary by benchmark and model, and that the DAG-based search shifts the learned verifier sets toward more structural and semantically grounded checks. We further show that exposing the discovered verifier set to an LLM as an external tool improves downstream accuracy by up to 17.0 points. We release our code

Pouya Pezeshkpour, Estevam Hruschka

Megagon Labs

LLM Evaluation LLM Answer Verification LLM-Based Program Synthesis LLM Reliability

Apr 24, 2026

Rethinking Math Reasoning Evaluation: A Robust LLM-as-a-Judge Framework Beyond Symbolic Rigidity

Recent advancements in large language models have led to significant improvements across various tasks, including mathematical reasoning, which is used to assess models' intelligence in logical reasoning and problem-solving. Models are evaluated on mathematical reasoning benchmarks by verifying the correctness of the final answer against a ground truth answer. A common approach for this verification is based on symbolic mathematics comparison, which fails to generalize across diverse mathematical representations and solution formats. In this work, we offer a robust and flexible alternative to rule-based symbolic mathematics comparison. We propose an LLM-based evaluation framework for evaluating model-generated answers, enabling accurate evaluation across diverse mathematical representations and answer formats. We present failure cases of symbolic evaluation in two popular frameworks, Lighteval and SimpleRL, and compare them to our approach, demonstrating clear improvements over commonly used methods. Our framework enables more reliable evaluation and benchmarking, leading to more accurate performance monitoring, which is important for advancing mathematical problem-solving and intelligent systems.

Erez Yosef, Oron Anschel, Shunit Haviv Hakimi +4

Tel-Aviv University · Amazon Prime Video · Ben-Gurion University

Mathematical Reasoning Benchmarks LLM Evaluation LLM-as-a-Judge LLM Answer Verification

Apr 24, 2026

BLAST: Benchmarking LLMs with ASP-based Structured Testing

Large Language Models (LLMs) have demonstrated remarkable performance across a broad spectrum of tasks, including natural language understanding, dialogue systems, and code generation. Despite evident progress, less attention has been paid to their effectiveness in handling declarative paradigms such as Answer Set Programming (ASP), to date. In this paper we introduce BLAST: The first dedicated benchmarking methodology and associated dataset for evaluating the accuracy of LLMs in generating ASP code. BLAST provides a structured evaluation framework featuring two novel semantic metrics tailored to ASP code generation. The paper presents the results of an empirical evaluation involving ten well-established graph-related problems from the ASP literature and a diverse set of eight state-of-the-art LLMs.

Manuel Alejandro Borroto Santana, Erica Coppolillo, Francesco Calimeri +3

University of Calabria, Rende, Italy · ICAR-CNR, Rende, Italy · Artificial Intelligence LAB, DeMaCS, University of Calabria, Rende, Italy +1

Logic Programming LLM Evaluation Language Model Generation Evaluation Answer Set Programming Code Generation Evaluation Code Generation Benchmarks+1

Apr 24, 2026

Verbal Confidence Saturation in 3-9B Open-Weight Instruction-Tuned LLMs: A Pre-Registered Psychometric Validity Screen

Verbal confidence elicitation is widely used to extract uncertainty estimates from LLMs. We tested whether seven instruction-tuned open-weight models (3-9B parameters, four families) produce verbalised confidence that meets minimal validity criteria for item-level Type-2 discrimination under minimal numeric elicitation with greedy decoding. In a pre-registered study (OSF: osf.io/azbvx), 524 TriviaQA items were administered under numeric (0-100) and categorical (10-class) elicitation to eight models at Q5_K_M quantisation on consumer hardware, yielding 8,384 deterministic trials. A psychometric validity screen was applied to each model-format cell. All seven instruct models were classified Invalid on numeric confidence (H2 confirmed, 7/7 vs. predicted >=4/7), with a mean ceiling rate of 91.7% (H1 confirmed). Categorical elicitation did not rescue validity. Instead, it disrupted task performance in six of seven models, producing accuracy below 5% (H4 not confirmed). Token-level logprobability did not usefully predict verbalised confidence under the observed variance regime (H5 confirmed, mean cross-validated R^2 < 0.01). Within the reasoning-distilled model, reasoning-trace length showed a strong negative partial correlation with confidence (rho = -0.36, p < .001), consistent with the Reasoning Contamination Effect. These results do not imply that internal uncertainty representations are absent. They show that minimal verbal elicitation fails to preserve internal signals at the output interface in this model-size regime. Psychometric screening should precede any downstream use of such signals.

Jon-Paul Cacioli

Independent Researcher, Melbourne, Australia

LLM Evaluation Confidence Estimation in Language Models Psychometric Validation LLM Reliability LLM Uncertainty Estimation Verbalized Confidence Estimation

Apr 24, 2026

An LLM-Native Psychometric Instrument Reveals a Self-Report--Behavior Gap Across 25 Models

Do large language models' (LLMs') answers to self-report questionnaires predict how they behave? Prior work finds they do not, but it uses human personality inventories, so the gap could reflect borrowed human constructs rather than LLM self-report itself. We test this with a self-report instrument built from LLM-specific behaviors (e.g., over-refusal, unsolicited disclaimers) whose structure is derived bottom-up. Administering 300 items 30 times to 25 LLMs from 17 developers yields five replicable, reliable factors (Tucker

φ\geq .957

,

α\geq .930

). We compare these self-reports with 2,500 open-ended behavioral samples rated by 151 humans and an LLM-judge ensemble. Humans and judges agree about model behavior (

\bar{r} = .51

), but self-report barely tracks human ratings (

\bar{r} = .09

, 95% CI

[-.07, .18]

) or rater-free text measures, and correcting for criterion unreliability leaves four of five factors near zero. Verbosity is the partial exception (

r = .40

, 71% of its reliability ceiling). On Responsiveness, self-report tracks LLM judges more than humans (

r = .53

vs.

.18

; Steiger

p = .04

), and controlling for length and formatting does not remove this: agreement between LLM judges and LLM self-report is weak evidence that either tracks human judgment.

Juan Manuel Contreras

Independent Researcher

LLM Evaluation Language Model Self-Assessment Psychometric Validation

Apr 24, 2026

When AI Speaks, Whose Values Does It Express? A Cross-Cultural Audit of Individualism-Collectivism Bias in Large Language Models

When you ask an AI assistant for advice about your career, your marriage, or a conflict with your family, does it give you the same answer regardless of where you are from? We tested this systematically by presenting three leading AI systems (Claude Sonnet 4.5, GPT-5.4, and Gemini 2.5 Flash) with ten real-life personal dilemmas, framed for users from 10 countries across 5 continents in 7 languages (n=840 scored responses). We compared AI advice against World Values Survey Wave 7 data measuring what people in each country actually believe. All three AI systems consistently gave Western-style, individualist advice even to users from societies that prioritize family, community, and authority, significantly more so than local values would predict (mean gap +0.76 on a 1-5 scale; t=15.65, p<0.001). The gap is largest for Nigeria (+1.85) and India (+0.82). Japan is the sole exception: AI systems treated Japanese users as more group-oriented than surveys show, revealing that AI encodes outdated stereotypes. Claude and GPT-5.4 show nearly identical bias magnitude, while Gemini is lower but still significant. The models diverge in mechanism: Claude shifts further collectivist in the user's native language; Gemini shifts more individualist; GPT-5.4 responds only to stated country identity. These findings point to a systemic homogenization of values across frontier AI. Data, code, and scoring pipeline are openly released.

Pruthvinath Jeripity Venkata

Independent Researcher

LLM Evaluation Cross-Cultural Language Model Evaluation Cultural Bias in Language Models Language Model Bias Evaluation

Apr 23, 2026

The Coin Flip Judge? Reliability and Bias in LLM-as-a-Judge Evaluation

LLM-as-a-Judge is now widely used to rank model outputs, train reward models, and populate public leaderboards, but its run-to-run reliability remains under-characterized. We study repeated identical evaluations on 29 tasks spanning 10 categories using two OpenAI judge models (GPT-4o-mini and GPT-4.1-mini), with 50 pairwise trials and 50 pointwise trials per question, supplemented by temperature and prompt-sensitivity ablations. Across judges, pairwise preferences flip on average 13.6% of the time, with 28% of questions exceeding a 20% flip rate and one question reaching 56%. GPT-4o-mini also exhibits a significant first-position bias (72% A-majority, p = 0.024). At the same time, mean pointwise score gaps are small (0.19--0.36 on a 10-point scale) and not statistically significant in aggregate, producing a pairwise--pointwise gap: judges frequently choose a winner even when their own scalar scores provide little evidence of a meaningful quality difference. Beyond within-judge instability, cross-judge agreement is only 76% (

κ= 0.51

), semantically equivalent prompt templates change majority outcomes in 25% of tested cases, and deterministic decoding reduces but does not eliminate inconsistency. A reliability curve analysis shows that, in our dataset, 11 repeated trials are needed for a majority vote to recover the 50-trial reference verdict with 95% probability on average, rising to 15 for high-variance questions. These findings suggest that single-trial LLM judging is often too noisy for high-stakes evaluation, and that multi-trial aggregation, position randomization, and explicit uncertainty reporting should be standard practice. Because both judges are from a single provider, cross-provider replication remains an important next step.

Abel Yagubyan

Independent Researcher

Inter-Rater Reliability LLM Evaluation Pairwise Comparison LLM-as-a-Judge Bias in LLM-as-a-Judge Position Bias

Apr 23, 2026

MathDuels: Evaluating LLMs as Problem Posers and Solvers

As frontier language models attain near-ceiling performance on static mathematical benchmarks, existing evaluations are increasingly unable to differentiate model capabilities, largely because they cast models solely as solvers of fixed problem sets. We introduce MathDuels, a self-play benchmark in which models occupy dual roles: each authors math problems under adversarial prompting and solves problems authored by every other participant. Problems are produced through a three-stage generation pipeline (meta-prompting, problem generation, and difficulty amplification), and validated by an independent verifier that excludes ill-posed questions. A Rasch model (Rasch, 1993) jointly estimates solver abilities and problem difficulties; author quality is derived from the difficulties of each model's authored problems. Experiments across 19 frontier models reveal that authoring and solving capabilities are partially decoupled, and that dual-role evaluation reveals capability separations invisible in single-role benchmarks. As newer models enter the arena, they produce problems that defeat previously dominant solvers, so the benchmark's difficulty co-evolves with participant strength rather than saturating at a fixed ceiling. We host a public leaderboard that updates as new models are released.

Zhiqiu Xu, Shibo Jin, Shreya Arya +1

Department of Computer and Information Science, University of Pennsylvania · Rabdos AI · Department of Mathematics, University of Pennsylvania

Mathematical Reasoning Benchmarks LLM Evaluation Mathematical Problem Generation LLM Mathematical Reasoning

Apr 23, 2026

Revisiting Non-Verbatim Memorization in Large Language Models: The Role of Entity Surface Forms

Understanding what kinds of factual knowledge large language models (LLMs) memorize is essential for evaluating their reliability and limitations. Entity-based QA is a common framework for analyzing non-verbatim memorization, but typical evaluations query each entity using a single canonical surface form, making it difficult to disentangle fact memorization from access through a particular name. We introduce RedirectQA, an entity-based QA dataset that uses Wikipedia redirect information to associate Wikidata factual triples with categorized surface forms for each entity, including alternative names, abbreviations, spelling variants, and common erroneous forms. Across 13 LLMs, we examine surface-conditioned factual memorization and find that prediction outcomes often change when only the entity surface form changes. This inconsistency is category-dependent: models are more robust to minor orthographic variations than to larger lexical variations such as aliases and abbreviations. Frequency analyses further suggest that both entity- and surface-level frequencies are associated with accuracy, and that entity frequency often contributes beyond surface frequency. Overall, factual memorization appears neither purely surface-specific nor fully surface-invariant, highlighting the importance of surface-form diversity in evaluating non-verbatim memorization.

Yuto Nishida, Naoki Shikoda, Yosuke Kishinami +4

Nara Institute of Science and Technology · Future Corporation

LLM Evaluation Memorization in Language Models Neural Network Memorization Memorization in Generative Models Factual Knowledge in Language Models Language Model Robustness+1

Apr 23, 2026

Who Defines "Best"? Towards Interactive, User-Defined Evaluation of LLM Leaderboards

LLM leaderboards are widely used to compare models and guide deployment decisions. However, leaderboard rankings are shaped by evaluation priorities set by benchmark designers, rather than by the diverse goals and constraints of actual users and organizations. A single aggregate score often obscures how models behave across different prompt types and compositions. In this work, we conduct an in-depth analysis of the dataset used in the LMArena (formerly Chatbot Arena) benchmark and investigate this evaluation challenge by designing an interactive visualization interface as a design probe. Our analysis reveals that the dataset is heavily skewed toward certain topics, that model rankings vary across prompt slices, and that preference-based judgments are used in ways that blur their intended scope. Building on this analysis, we introduce a visualization interface that allows users to define their own evaluation priorities by selecting and weighting prompt slices and to explore how rankings change accordingly. A qualitative study suggests that this interactive approach improves transparency and supports more context-specific model evaluation, pointing toward alternative ways to design and use LLM leaderboards.

Minji Jung, Minjae Lee, Yejin Kim +2

Yonsei University, South Korea

LLM Evaluation Human-in-the-Loop Evaluation

Apr 23, 2026

A Metamorphic Testing Approach to Diagnosing Memorization in LLM-Based Program Repair

LLM-based automated program repair (APR) techniques have shown promising results in reducing debugging costs. However, prior results can be affected by data leakage: large language models (LLMs) may memorize bug fixes when evaluation benchmarks overlap with their pretraining data, leading to inflated performance estimates. In this paper, we investigate whether we can better reveal data leakage by combining metamorphic testing (MT) with negative log-likelihood (NLL), which has been used in prior work as a proxy for memorization. We construct variant benchmarks by applying semantics-preserving transformations to two widely used datasets, Defects4J and GitBug-Java. Using these benchmarks, we evaluate the repair success rates of seven LLMs on both original and transformed versions, and analyze the relationship between performance degradation and NLL. Our results show that all evaluated state-of-the-art LLMs exhibit substantial drops in patch generation success rates on transformed benchmarks, ranging from -4.1% for GPT-4o to -15.98% for Llama-3.1. Furthermore, we find that this degradation strongly correlates with NLL on the original benchmarks, suggesting that models perform better on instances they are more likely to have memorized. These findings show that combining MT with NLL provides stronger and more reliable evidence of data leakage, while metamorphic testing alone can help mitigate its effects in LLM-based APR evaluations.

Milan De Koning, Ali Asgari, Pouria Derakhshanfar +1

JetBrains Research, Amsterdam, The Netherlands · Delft University of Technology, Delft, The Netherlands

LLM Evaluation Metamorphic Testing Automated Program Repair LLM Memory

Apr 23, 2026

OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving

While Large Language Models (LLMs) demonstrate remarkable reasoning, complex optimization tasks remain challenging, requiring domain knowledge and robust implementation. However, existing benchmarks focus narrowly on Mathematical Programming and Combinatorial Optimization, hindering comprehensive evaluation. To address this, we introduce OptiVerse, a comprehensive benchmark of 1,000 curated problems spanning neglected domains, including Stochastic Optimization, Dynamic Optimization, Game Optimization, and Optimal Control, across three difficulty levels: Easy, Medium, and Hard. The experiments with 22 LLMs of different sizes reveal sharp performance degradation on hard problems, where even advanced models like GPT-5.2 and Gemini-3 struggle to exceed 27% accuracy. Through error analysis, we identify that modeling & logic errors remain the primary bottleneck. Consequently, we propose a Dual-View Auditor Agent that improves the accuracy of the LLM modeling process without introducing significant time overhead. OptiVerse will serve as a foundational platform for advancing LLMs in solving complex optimization challenges.

Xinyu Zhang, Boxuan Zhang, Yuchen Wan +5

School of Computer Science and Technology, Xi’an Jiaotong University · 2Ministry of Education Key Laboratory of Intelligent Networks and Network Security, China · 4Lenovo Research +1

LLM Evaluation Benchmark Design Large Language Model-Guided Optimization Natural Language to Optimization Modeling

Apr 23, 2026

Evaluating AI Meeting Summaries with a Reusable Cross-Domain Pipeline

Industrial teams often deploy large language model features before stable regression or model selection evaluation exists. We present a reusable evaluation system for AI meeting summaries that combines structured ground-truth (GT) construction, fixed candidate generation, claim-grounded scoring, persisted reporting, and a privacy-bounded online monitoring and nomination interface. The online evidence is not itself a benchmark: privacy-safe aggregate exports show active monitoring, hard regime detection, and directional movement without exposing customer data. We benchmark the offline path on 114 meetings across city_council, private_data, and whitehouse_press_briefings, yielding 340 completed meeting-model pairs and 680 judge runs for gpt-4.1-mini, gpt-5-mini, and gpt-5.1. Under this fixed protocol, accuracy differences are not statistically significant under Holm correction (corrected p-values 0.053-0.448), although gpt-4.1-mini has the highest mean accuracy (0.583); the significant separation is on retention, where gpt-5.1 leads on completeness (0.886) and coverage (0.942). Typed slices isolate whitehouse_press_briefings as an accuracy-hard regime, and a later focused rerun over gpt-4.1, gpt-5-mini, and gpt-5.4 reuses the same stack under the same judges and metrics. This extended preprint keeps those core results aligned with the formal submission while adding a more detailed repository-level account of cross-domain reuse from the companion AI-search paper and an additional typed DeepEval contrastive analysis. Model naming note. Running text uses canonical model names on first introduction. Tables, filenames, and artifact IDs retain compact report labels for consistency with the packaged benchmark outputs. Table A maps the two conventions and is repeated in Section 4.3 where candidate-generation settings are defined.

Philip Zhong, Don Wang, Jason Zhang

Webex Suite AI Cisco Systems, Inc. San Jose, California, USA

LLM Evaluation Factual Consistency Evaluation

Apr 23, 2026

EngramaBench: Evaluating Long-Term Conversational Memory with Structured Graph Retrieval

Large language model assistants are increasingly expected to retain and reason over information accumulated across many sessions. We introduce EngramaBench, a benchmark for long-term conversational memory built around five personas, one hundred multi-session conversations, and one hundred fifty queries spanning factual recall, cross-space integration, temporal reasoning, adversarial abstention, and emergent synthesis. We evaluate Engrama, a graph-structured memory system, against GPT-4o full-context prompting and Mem0, an open-source vector-retrieval memory system. All three use the same answering model (GPT-4o), isolating the effect of memory architecture. GPT-4o full-context achieves the highest composite score (0.6186), while Engrama scores 0.5367 globally but is the only system to score higher than full-context prompting on cross-space reasoning (0.6532 vs. 0.6291, n=30). Mem0 is cheapest but substantially weaker (0.4809). Ablations reveal that the components driving Engrama's cross-space advantage trade off against global composite score, exposing a systems-level tension between structured memory specialization and aggregate optimization.

Julian Acuna

Long-Term Conversational Memory LLM Evaluation Memorization in Language Models Persistent Memory for Language Models Memorization in Generative Models Memory Agent Benchmarks+2

Apr 23, 2026

A Demonstration of SQLyzr: A Platform for Fine-Grained Text-to-SQL Evaluation and Analysis

Text-to-SQL models have significantly improved with the adoption of Large Language Models (LLMs), leading to their increasing use in real-world applications. Although many benchmarks exist for evaluating the performance of text-to-SQL models, they often rely on a single aggregate score, lack evaluation under realistic settings, and provide limited insight into model behaviour across different query types. In this work, we present SQLyzr, a comprehensive benchmark and evaluation platform for text-to-SQL models. SQLyzr incorporates a diverse set of evaluation metrics that capture multiple aspects of generated queries, while enabling more realistic evaluation through workload alignment with real-world SQL usage patterns and database scaling. It further supports fine-grained query classification, error analysis, and workload augmentation, allowing users to better diagnose and improve text-to-SQL models. This demonstration showcases these capabilities through an interactive experience. Through SQLyzr's graphical interface, users can customize evaluation settings, analyze fine-grained reports, and explore additional features of the platform. We envision that SQLyzr facilitates the evaluation and iterative improvement of text-to-SQL models by addressing key limitations of existing benchmarks. The source code of SQLyzr is available at https://github.com/sepideh-abedini/SQLyzr.

Sepideh Abedini, M. Tamer Özsu

University of Waterloo

LLM Evaluation Text-to-SQL Text-to-SQL Evaluation

Apr 22, 2026

SpeechParaling-Bench: A Comprehensive Benchmark for Paralinguistic-Aware Speech Generation

Paralinguistic cues are essential for natural human-computer interaction, yet their evaluation in Large Audio-Language Models (LALMs) remains limited by coarse feature coverage and the inherent subjectivity of assessment. To address these challenges, we introduce SpeechParaling-Bench, a comprehensive benchmark for paralinguistic-aware speech generation. It expands existing coverage from fewer than 50 to over 100 fine-grained features, supported by more than 1,000 English-Chinese parallel speech queries, and is organized into three progressively challenging tasks: fine-grained control, intra-utterance variation, and context-aware adaptation. To enable reliable evaluation, we further develop a pairwise comparison pipeline, in which candidate responses are evaluated against a fixed baseline by an LALM-based judge. By framing evaluation as relative preference rather than absolute scoring, this approach mitigates subjectivity and yields more stable and scalable assessments without costly human annotation. Extensive experiments reveal substantial limitations in current LALMs. Even leading proprietary models struggle with comprehensive static control and dynamic modulation of paralinguistic features, while failure to correctly interpret paralinguistic cues accounts for 43.3% of errors in situational dialogue. These findings underscore the need for more robust paralinguistic modeling toward human-aligned voice assistants.

Ruohan Liu, Shukang Yin, Tao Wang +6

1Nanjing University · 2Xiaomi

Audio-Language Model Evaluation LLM Evaluation Speech Generation Evaluation Pairwise Preference Evaluation Audio-Language Models Generative AI Evaluation

Apr 22, 2026

Diagnosing CFG Interpretation in LLMs

As LLMs are increasingly integrated into agentic systems, they must adhere to dynamically defined, machine-interpretable interfaces. We evaluate LLMs as in-context interpreters: given a novel context-free grammar, can LLMs generate syntactically valid, behaviorally functional, and semantically faithful outputs? We introduce RoboGrid, a framework that disentangles syntax, behavior, and semantics through controlled stress-tests of recursion depth, expression complexity, and surface styles. Our experiments reveal a consistent hierarchical degradation: LLMs often maintain surface syntax but fail to preserve structural semantics. Despite the partial mitigation provided by CoT reasoning, performance collapses under structural density, specifically deep recursion and high branching, with semantic alignment vanishing at extreme depths. Furthermore, "Alien" lexicons reveal that LLMs rely on semantic bootstrapping from keywords rather than pure symbolic induction. These findings pinpoint critical gaps in hierarchical state-tracking required for reliable, grammar-agnostic agents.

Hanqi Li, Lu Chen, Kai Yu

1X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · 3Shanghai Innovation Institution, Shanghai, China · 4Jiangsu Key Lab of Language Computing, Suzhou, China +2

LLM Evaluation In-Context Learning LLM Agent Reliability Compositional Generalization

Apr 22, 2026

Exploiting LLM-as-a-Judge Disposition on Free Text Legal QA via Prompt Optimization

This work explores the role of prompt design and judge selection in LLM-as-a-Judge evaluations of free text legal question answering. We examine whether automatic task prompt optimization improves over human-centered design, whether optimization effectiveness varies by judge feedback style, and whether optimized prompts transfer across judges. We systematically address these questions on the LEXam benchmark by optimizing task prompts using the ProTeGi method with feedback from two judges (Qwen3-32B, DeepSeek-V3) across four task models, and then testing cross-judge transfer. Automatic optimization consistently outperforms the baseline, with lenient judge feedback yielding higher and more consistent gains than strict judge feedback. Prompts optimized with lenient feedback transfer better to strict judges than the reverse direction. Analysis reveals that lenient judges provide permissive feedback, yielding prompts with broader applicability, whereas strict judges produce restrictive feedback, leading to judge-specific overfitting. Our findings demonstrate algorithmically optimizing prompts on training data can outperform human-centered prompt design and that judges' dispositions during optimization shape prompt generalizability.

Mohamed Hesham Elganayni, Runsheng Chen, Sebastian Nagl +1

Technical University of Munich Germany

LLM Evaluation LLM-as-a-Judge Automatic Prompt Optimization Legal QA

Apr 22, 2026

Cross-Dataset Bloom Question Classification: Supervised Models and Prompted LLMs

Automatic Bloom's taxonomy classification of assessment questions can substantially reduce instructor workload, but labeling is subjective and teacher-dependent. Prior machine learning (ML) and deep learning (DL) approaches reported strong within-dataset results, yet were rarely evaluated in cross-dataset settings, leaving real-world generalizability unclear; meanwhile, LLM effectiveness for Bloom question classification has not been systematically studied. We evaluated the cross-dataset generalization of existing ML/DL methods and assessed LLMs with multiple prompting strategies on five datasets; the best prompting strategy combined in-context examples with course-specific action verbs. Supervised ML/DL models degraded substantially on unseen datasets, whereas LLMs were more stable, suggesting a robust alternative across diverse educational contexts. Based on the best prompting strategy, we also presented a lightweight UI that supports instructors in automatically classifying large question banks; a usability study indicated low workload and high usability.

Abdolali Faraji, Mohammadreza Molavi, Zohreh Rasoulkhani +2

Leibniz Information Centre for Science and Technology (TIB) · University of Genoa

LLM Evaluation Educational Assessment LLM Prompting Classification Cross-Dataset Generalization Education

Apr 22, 2026

Early-Stage Product Line Validation Using LLMs: A Study on Semi-Formal Blueprint Analysis

We study whether Large Language Models (LLMs) can perform feature model analysis operations (AOs) directly on semi-formal textual blueprints, i.e., concise constrained-language descriptions of feature hierarchies and constraints, enabling early validation in Software Product Line scoping. Using 12 state-of-the-art LLMs and 16 standard AOs, we compare their outputs against the solver-based oracle FLAMA. Results show that reasoning-optimized models (e.g., Grok 4 Fast Reasoning, Gemini 2.5 Pro) achieve 88-89% average accuracy across all evaluated blueprints and operations, approaching solver correctness. We identify systematic errors in structural parsing and constraint reasoning, and highlight accuracy-cost trade-offs that inform model selection. These findings position LLMs as lightweight assistants for early variability validation.

Viet-Man Le, Thi Ngoc Trang Tran, Sebastian Lubos +2

Graz University of Technology Graz, Austria

Software Engineering LLM Evaluation LLM Reasoning

Apr 22, 2026

Benchmarking Large Language Models for Safety Data Extraction

Accurate extraction of structured information from Safety Data Sheets (SDS) remains challenging in industrial safety due to heterogeneous document formats and the limitations of traditional rule-based methods. This study benchmarks state-of-the-art Large Language Models (LLMs) for automated SDS data extraction, comparing text-based and multimodal processing pipelines. We systematically evaluate four models: Gemini 1.5 Pro, GPT-4o, Claude 3.7 Sonnet, and Llama 3.1-70B, across three prompting strategies: zero-shot, few-shot, and chain-of-thought. The evaluation framework assessed accuracy, latency, and cost across more than 50,000 extracted data fields. Results show that text-based extraction consistently outperforms multimodal processing across all metrics. Gemini 1.5 Pro combined with a Chain-of-Thought prompt achieved the highest accuracy (84%), outperforming GPT-4o (81%) and Claude 3.7 Sonnet (79%). However, no model surpassed the 90% accuracy threshold commonly required for reliable real-world deployment. These findings indicate that general-purpose LLMs are not yet robust enough for unsupervised industrial use, though performance suggests strong potential with task-specific fine-tuning. Future research should focus on domain-adapted training, model calibration, and the integration of Human-in-the-Loop verification to ensure safety-critical reliability.

Jonas Grill, Thomas Bayer, Sören Berlinger

1SAP SE, Germany. · Institute for Digital Transformation, Ravensburg-Weingarten University.

LLM Evaluation LLM Prompting Document Information Extraction Multimodal Large Language Models LLM Information Extraction

Apr 22, 2026

DialToM: A Theory of Mind Benchmark for Forecasting State-Driven Dialogue Trajectories

We introduce DialToM, an annotated Theory of Mind (ToM) benchmark built from naturalistic human-human dialogues using a multiple-choice evaluation framework. Concurrent with recent work showing a gap between explicit mental-state inference and applied ToM in synthetic settings~\cite{gu2024simpletom}, we establish a stricter State-Driven Diagnostic Probe in which models must forecast state-consistent dialogue trajectories solely from isolated mental-state profiles without dialogue context. Our evaluation reveals a systematic reasoning asymmetry -- LLMs excel at inferring mental states (Literal ToM) but struggle to leverage them for social forecasting (Functional ToM). Crucially, a domain expert achieves 100% accuracy on this task, proving its validity and establishing a stark human-AI capability gap. Further, a teacher-student reasoning injection probe shows that Gemini 3 Pro -- which establishes the leading baseline -- possesses robust Functional ToM capabilities for context-free forecasting that are transferable to weaker models. DialToM, its evaluation code, and dataset are publicly available at https://github.com/Stealth-py/DialToM.

Neemesh Yadav, Palakorn Achananuparp, Jing Jiang +1

Singapore Management University · Australian National University

LLM Evaluation Theory of Mind

Apr 22, 2026

CyberCertBench: Evaluating LLMs in Cybersecurity Certification Knowledge

The rapid evolution and use of Large Language Models (LLMs) in professional workflows require an evaluation of their domain-specific knowledge against industry standards. We introduceCyberCertBench, a new suite of Multiple Choice Question Answering (MCQA) benchmarks derived from industry recognized certifications. CyberCertBench evaluates LLM domain knowledgeagainst the professional standards of Information Technology cybersecurity and more specializedareas such as Operational Technology and related cybersecurity standards. Concurrently, we propose and validate a novel Proposer-Verifier framework, a methodology to generate interpretable,natural language explanations for model performance. Our evaluation shows that frontier modelsachieve human expert level in general networking and IT security knowledge. However, theiraccuracy declines in questions that require vendor-specific nuances or knowledge in formalstandards, like, e.g., IEC 62443. Analysis of model scaling trend and release date demonstratesremarkable gains in parameter efficiency, while recent larger models show diminishing returns.Code and evaluation scripts are available at: https://github.com/GKeppler/CyberCertBench.

Gustav Keppler, Ghada Elbez, Veit Hagenmeyer

Institute for Automation and Applied Informatics (IAI), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany

LLM Evaluation Cybersecurity LLMs for Cybersecurity

Apr 22, 2026

ActuBench: A Multi-Agent LLM Pipeline for Generation and Evaluation of Actuarial Reasoning Tasks

We present ActuBench, a multi-agent LLM pipeline for the automated generation and evaluation of advanced actuarial assessment items aligned with the International Actuarial Association (IAA) Education Syllabus. The pipeline separates four LLM roles by adapter: one agent drafts items, one constructs distractors, a third independently verifies both stages and drives bounded one-shot repair loops, and a cost-optimized auxiliary agent handles Wikipedia-note summarization and topic labelling. The items, per-model responses and complete leaderboard are published as a browsable web interface at https://actubench.de/en/, allowing readers and practitioners to inspect individual items without a repository checkout. We evaluate 50 language models from eight providers on two complementary benchmarks -- 100 empirically hardest multiple-choice items and 100 open-ended items scored by an LLM judge -- and report three headline findings. First, multi-agent verification is load-bearing: the independent verifier flags a majority of drafted items on first pass, most of which the one-shot repair loop resolves. Second, locally-hosted open-weights inference sits on the cost-performance Pareto front: a Gemma~4 model running on consumer hardware and a Cerebras-hosted 120B open-weights model dominate the near-zero-cost region, with the latter within one item of the top of the leaderboard. Third, MCQ and LLM-as-Judge rankings differ meaningfully: the MCQ scaffold inflates the performance ceiling, and Judge-mode evaluation is needed to discriminate at the frontier.

Jan-Philipp Schmidt

TH Köln, Institut für Versicherungswesen (ivwKöln)

LLM Evaluation Educational Assessment AI in Education Multi-Agent LLMs

Apr 22, 2026

The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models

Evaluating the multilingual and multicultural capabilities of Large Language Models (LLMs) is essential for their global utility. However, current benchmarks face three critical limitations: (1) fragmented evaluation dimensions that often neglect deep cultural nuances; (2) insufficient language coverage in subjective tasks relying on low-quality machine translation; and (3) shallow analysis that lacks diagnostic depth beyond simple rankings. To address these, we introduce GaoYao, a comprehensive benchmark with 182.3k samples, 26 languages and 51 nations/areas. First, GaoYao proposes a unified framework categorizing evaluation tasks into three cultural layers (General Multilingual, Cross-cultural, Monocultural) and nine cognitive sub-layers. Second, we achieve native-quality expansion by leveraging experts to rigorously localize subjective benchmarks into 19 languages and synthesizing cross-cultural test sets for 34 cultures, surpassing prior coverage by up to 111%. Third, we conduct an in-depth diagnostic analysis on 20+ flagship and compact LLMs. Our findings reveal significant geographical performance disparities and distinct gaps between tasks, offering a reliable map for future work. We release the benchmark (https://github.com/lunyiliu/GaoYao).

Yilun Liu, Chunguang Zhao, Mengyao Piao +14

Huawei, China · Fudan University, China

Multilingual Language Model Evaluation LLM Evaluation Cross-Cultural Language Model Evaluation Cultural Knowledge in Language Models