{"total":113,"rows":[{"id":"2511.04703","title":"Measuring what Matters: Construct Validity in Large Language Model Benchmarks","created":"2025-11-03","cited_by_count":119,"area":null},{"id":"2503.01622","title":"DOVE: A Large-Scale Multi-Dimensional Predictions Dataset Towards Meaningful LLM Evaluation","created":"2025-03-03","cited_by_count":21,"area":null},{"id":"2603.13285","title":"Brittlebench: Quantifying LLM robustness via prompt sensitivity","created":"2026-02-27","cited_by_count":21,"area":null},{"id":"2509.16533","title":"Challenging the Evaluator: LLM Sycophancy Under User Rebuttal","created":"2025-09-20","cited_by_count":18,"area":null},{"id":"2502.04295","title":"Beyond Prompt Content: Enhancing LLM Performance via Content-Format Integrated Prompt Optimization","created":"2025-02-06","cited_by_count":16,"area":null},{"id":"2507.22168","title":"Persona-Augmented Benchmarking: Evaluating LLMs Across Diverse Writing Styles","created":"2025-07-29","cited_by_count":16,"area":null},{"id":"2502.14359","title":"Triangulating LLM Progress through Benchmarks, Games, and Cognitive Tests","created":"2025-02-20","cited_by_count":12,"area":null},{"id":"2505.22169","title":"ReliableEval: A Recipe for Stochastic LLM Evaluation via Method of Moments","created":"2025-05-28","cited_by_count":11,"area":null},{"id":"2508.11383","title":"When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs","created":"2025-08-15","cited_by_count":10,"area":null},{"id":"2604.23478","title":"JudgeSense: A Benchmark for Prompt Sensitivity in LLM-as-a-Judge Systems","created":"2026-04-26","cited_by_count":10,"area":null},{"id":"2504.13644","title":"Exploring the Potential for Large Language Models to Demonstrate Rational Probabilistic Beliefs","created":"2025-04-18","cited_by_count":9,"area":null},{"id":"2508.19432","title":"Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs","created":"2025-08-26","cited_by_count":9,"area":null},{"id":"2505.21701","title":"Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2603.05651","title":"The Fragility Of Moral Judgment In Large Language Models","created":"2026-03-05","cited_by_count":8,"area":null},{"id":"2509.03036","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","created":"2025-09-03","cited_by_count":7,"area":null},{"id":"2506.17442","title":"Keeping Medical AI Healthy and Trustworthy: A Review of Detection and Correction Methods for System Degradation","created":"2025-06-20","cited_by_count":6,"area":null},{"id":"2601.15812","title":"ErrorMap and ErrorAtlas: Charting the Failure Landscape of Large Language Models","created":"2026-01-22","cited_by_count":6,"area":null},{"id":"2508.08096","title":"Limits of LLM Text Detectors in Education","created":"2025-08-11","cited_by_count":5,"area":null},{"id":"2508.16838","title":"If We May De-Presuppose: Robustly Verifying Claims through Presupposition-Free Question Decomposition","created":"2025-08-22","cited_by_count":5,"area":null},{"id":"2510.25356","title":"Prompting from the bench: Large-scale pretraining is not sufficient to prepare LLMs for ordinary meaning analysis","created":"2025-10-29","cited_by_count":4,"area":null},{"id":"2511.21695","title":"EvalCards: A Framework for Standardized Evaluation Reporting","created":"2025-11-05","cited_by_count":4,"area":null},{"id":"2504.03975","title":"GREATERPROMPT: A Unified, Customizable, and High-Performing Open-Source Toolkit for Prompt Optimization","created":"2025-04-04","cited_by_count":3,"area":null},{"id":"2505.12938","title":"Leveraging LLM Inconsistency to Boost Pass@k Performance","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2506.03360","title":"A Multimodal, Multilingual, and Multidimensional Pipeline for Fine-grained Crowdsourcing Earthquake Damage Evaluation","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2507.21117","title":"A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges","created":"2025-07-17","cited_by_count":3,"area":null},{"id":"2509.01787","title":"AHAMask: Reliable Task Specification for Large Audio Language Models without Instructions","created":"2025-09-01","cited_by_count":3,"area":null},{"id":"2509.22506","title":"Representing LLMs in Prompt Semantic Task Space","created":"2025-09-26","cited_by_count":3,"area":null},{"id":"2510.23558","title":"ISA-Bench: Benchmarking Instruction Sensitivity for Large Audio Language Models","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2601.08064","title":"Calibration Is Not Enough: Evaluating Confidence Estimation Under Language Variations","created":"2026-01-12","cited_by_count":3,"area":null},{"id":"2604.18389","title":"Understanding the Prompt Sensitivity","created":"2026-04-20","cited_by_count":3,"area":null},{"id":"2605.21318","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","created":"2026-05-20","cited_by_count":3,"area":null},{"id":"2502.18798","title":"Choices Speak Louder than Questions","created":"2025-02-26","cited_by_count":2,"area":null},{"id":"2505.23996","title":"Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2509.10414","title":"Is In-Context Learning Learning?","created":"2025-09-12","cited_by_count":2,"area":null},{"id":"2509.19590","title":"Position: AI Evaluations Should be Grounded on a Theory of Capability","created":"2025-09-23","cited_by_count":2,"area":null},{"id":"2510.02025","title":"Style over Story: Measuring LLM Narrative Preferences via Structured Selection","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2601.03120","title":"A framework for assuring the accuracy and fidelity of an AI-enabled Digital Twin of en route UK airspace","created":"2026-01-06","cited_by_count":2,"area":null},{"id":"2602.02605","title":"Fine-Tuning Language Models to Know What They Know","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2603.26539","title":"How Open Must Language Models be to Enable Reliable Scientific Inference?","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2605.09115","title":"AI Native Asset Intelligence","created":"2026-05-09","cited_by_count":2,"area":null},{"id":"2605.30646","title":"Same Patient, Different Words, Different Diagnosis? Evaluating Semantic Stability in Clinical LLMs","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2607.12963","title":"The Illusion of Robustness: Aggregate Accuracy Hides Prediction Flips under Task-Irrelevant Context","created":"2026-07-14","cited_by_count":2,"area":null},{"id":"2501.15351","title":"Fairness in LLM-Generated Surveys","created":"2025-01-25","cited_by_count":1,"area":null},{"id":"2502.01243","title":"OphthBench: A Comprehensive Benchmark for Evaluating Large Language Models in Chinese Ophthalmology","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2504.03822","title":"Arti-\"fickle\" Intelligence: Using LLMs as a Tool for Inference in the Political and Social Sciences","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2506.06540","title":"Large Language Models Can Be a Viable Substitute for Expert Political Surveys When a Shock Disrupts Traditional Measurement Approaches","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2506.16584","title":"Measuring Intent Comprehension in LLMs","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2506.17369","title":"Re-Evaluating Code LLM Benchmarks Under Semantic Mutation","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2507.07539","title":"CEA-LIST at CheckThat! 2025: Evaluating LLMs as Detectors of Bias and Opinion in Text","created":"2025-07-10","cited_by_count":1,"area":null},{"id":"2507.10326","title":"Grammar-Guided Evolutionary Search for Discrete Prompt Optimisation","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2508.13948","title":"Prompt Orchestration Markup Language","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2509.02363","title":"Towards Temporal Knowledge-Base Creation for Fine-Grained Opinion Analysis with Language Models","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2510.22823","title":"Cross-Lingual Stability and Bias in Instruction-Tuned Language Models for Humanitarian NLP","created":"2025-10-26","cited_by_count":1,"area":null},{"id":"2511.19956","title":"Prompt Fairness: Sub-group Disparities in LLMs","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2512.22742","title":"Robust LLM-based Column Type Annotation via Prompt Augmentation with LoRA Tuning","created":"2025-12-28","cited_by_count":1,"area":null},{"id":"2602.04604","title":"Beyond Holistic Scores: Automatic Trait-Based Quality Scoring of Argumentative Essays","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2603.03298","title":"TATRA: Training-Free Instance-Adaptive Prompting Through Rephrasing and Aggregation","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2603.21373","title":"PLR: Plackett-Luce for Reordering In-Context Learning Examples","created":"2026-03-22","cited_by_count":1,"area":null},{"id":"2604.23267","title":"Fine-tuning vs. In-context Learning in Large Language Models: A Formal Language Learning Perspective","created":"2026-04-25","cited_by_count":1,"area":null},{"id":"2605.06937","title":"A Reproducible Optimisation Protocol for Calibrating Prompt-Based Large Language Model Workflows in Evidence Synthesis","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.11206","title":"Instructions Shape Production of Language, not Processing","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2606.04109","title":"Discourse-Role Labels as Presentation-Time Variables for Context Use in Language Models","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2607.26762","title":"Relation Geometry in Semantic Space of Language Models","created":"2026-07-29","cited_by_count":1,"area":null},{"id":"2608.15630","title":"Do Assessment Instruments Measure the Same Thing for Humans and LLMs? A Latent Structure Analysis","created":"2026-08-16","cited_by_count":1,"area":null},{"id":"2503.19265","title":"PHEONA: An Evaluation Framework for Large Language Model-based Approaches to Computational Phenotyping","created":"2025-03-25","cited_by_count":0,"area":null},{"id":"2504.20469","title":"Fane at SemEval-2025 Task 10: Zero-Shot Entity Framing with Large Language Models","created":"2025-04-29","cited_by_count":0,"area":null},{"id":"2505.03053","title":"Developing A Framework to Support Human Evaluation of Bias in Generated Free Response Text","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2507.06329","title":"MixAssist: An Audio-Language Dataset for Co-Creative AI Assistance in Music Mixing","created":"2025-07-08","cited_by_count":0,"area":null},{"id":"2508.06017","title":"Position: Intelligent Coding Systems Should Write Programs with Justifications","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2508.10108","title":"Amazon Nova AI Challenge -- Trusted AI: Advancing secure, AI-assisted software development","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2509.01053","title":"A Dynamic Fusion Model for Consistent Crisis Response","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2511.18616","title":"What Helps Language Models Predict Human Beliefs: Demographics or Prior Stances?","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2512.12444","title":"Can GPT replace human raters? Validity and reliability of machine-generated norms for metaphors","created":"2025-12-13","cited_by_count":0,"area":null},{"id":"2601.16753","title":"Standardizing Longitudinal Radiology Report Evaluation via Large Language Model Annotation","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2601.16800","title":"Large Language Models as Automatic Annotators and Annotation Adjudicators for Fine-Grained Opinion Analysis","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2601.22373","title":"Stability-Aware Prompt Optimization for Clinical Data Abstraction","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.11179","title":"From Instruction to Output: The Role of Prompting in Modern NLG","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2603.10477","title":"PEEM: Prompt Engineering Evaluation Metrics for Interpretable Joint Evaluation of Prompts and Responses","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2603.16245","title":"How to Utilize Complementary Vision-Text Information for 2D Structure Understanding","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.19782","title":"KoALa-Bench: Evaluating Large Audio Language Models on Korean Speech Understanding and Faithfulness","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.22142","title":"Voice Under Revision: Large Language Models and the Normalization of Personal Narrative","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.01727","title":"Are LLMs More Skeptical of Entertainment News?","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2605.03092","title":"Semantically Enriching Investor Micro-blogs for Opinion-Aware Emotion Analysis: A Practical Approach","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.03618","title":"BIT.UA-AAUBS at ArchEHR-QA 2026: Evaluating Open-Source and Proprietary LLMs via Prompting in Low-Resource QA","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.06327","title":"Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.07093","title":"The Translation Tax Is Not a Scalar: A Counterfactual Audit of English-Source Cue Inheritance in Chinese Multilingual Benchmarks","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.08522","title":"Coordinates of Capability: A Unified MTMM-Geometric Framework for LLM Evaluation","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.13412","title":"LLMs as annotators of credibility assessment in Danish asylum decisions: evaluating classification performance and errors beyond aggregated metrics","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.29678","title":"Spurious Prompts: Can Irrelevant Prompts Steer Large Language Models?","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2605.30913","title":"Toxic HallucinAItions: Perturbing Prompts and Tracing LLM Circuits","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.15521","title":"Emergent retokenization symmetry in large language models: phenomenology and applications","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2606.16127","title":"AuAu: A Benchmark for Auditing Authoritarian Alignment in Large Language Models","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.22797","title":"Measuring Behavior Portability in Large Language Models","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.27314","title":"Beyond Surface Forms: A Comprehensive, Mechanism-Oriented Taxonomy of Indirect Linguistic Encoding for LLM-Based Coded Language Detection","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.15957","title":"From Plausible to Actionable: A Position on LLM Self-Explanations","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2607.22683","title":"Imprompt: A Language Framework for Prompt Programming","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.00828","title":"Isotropy Cliffs: The Geometric Signature of Decision-Making in Large Language Models","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2608.11513","title":"Do Influence Tactics Matter? Investigating Prompt Framing Effects in LLM Code Generation","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.17810","title":"Interpretable Humans, Alien LLMs: Expert Analysis of Latent Structures in Assessment Responses","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.18108","title":"Same Facts, Different Updates: Inference Setup Shapes LLM Behavior in Medical Allocation","created":"2026-06-10","cited_by_count":0,"area":null}],"next_cursor":"100"}