{"total":149,"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":"2412.13147","title":"Are Your LLMs Capable of Stable Reasoning?","created":"2024-12-17","cited_by_count":65,"area":"lr"},{"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":"2602.07150","title":"On Randomness in Agentic Evals","created":"2026-02-06","cited_by_count":17,"area":"agents"},{"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":"2504.03255","title":"Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective","created":"2025-04-04","cited_by_count":13,"area":"agents"},{"id":"2509.03986","title":"Promptception: How Sensitive Are Large Multimodal Models to Prompts?","created":"2025-09-04","cited_by_count":13,"area":"mllm"},{"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":"2604.02547","title":"Beyond Resolution Rates: Behavioral Drivers of Coding Agent Success and Failure","created":"2026-04-02","cited_by_count":11,"area":"lr"},{"id":"2503.05587","title":"Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data","created":"2025-03-07","cited_by_count":10,"area":"rag"},{"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":"2509.01301","title":"Culture is Everywhere: A Call for Intentionally Cultural Evaluation","created":"2025-09-01","cited_by_count":10,"area":"alignment"},{"id":"2511.03369","title":"Silenced Biases: The Dark Side LLMs Learned to Refuse","created":"2025-11-05","cited_by_count":10,"area":"alignment"},{"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":"2505.14412","title":"PRL: Prompts from Reinforcement Learning","created":"2025-05-20","cited_by_count":9,"area":"lr"},{"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":"2603.00131","title":"Thought Virus: Viral Misalignment via Subliminal Prompting in Multi-Agent Systems","created":"2026-02-23","cited_by_count":9,"area":"lr"},{"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":"2509.13588","title":"CoBRA: Programming Cognitive Bias in Social Agents Using Classic Social Science Experiments","created":"2025-09-16","cited_by_count":8,"area":"agents"},{"id":"2510.01032","title":"Meaningless Tokens, Meaningful Gains: How Activation Shifts Enhance LLM Reasoning","created":"2025-10-01","cited_by_count":8,"area":"lr"},{"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":"2502.16280","title":"Human Preferences in Large Language Model Latent Space: A Technical Analysis on the Reliability of Synthetic Data in Voting Outcome Prediction","created":"2025-02-22","cited_by_count":5,"area":"synth"},{"id":"2508.08096","title":"Limits of LLM Text Detectors in Education","created":"2025-08-11","cited_by_count":5,"area":null},{"id":"2508.15253","title":"Conflict-Aware Soft Prompting for Retrieval-Augmented Generation","created":"2025-08-21","cited_by_count":5,"area":"rag"},{"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":"2508.06056","title":"RAGTrace: Understanding and Refining Retrieval-Generation Dynamics in Retrieval-Augmented Generation","created":"2025-08-08","cited_by_count":4,"area":"rag"},{"id":"2509.00482","title":"Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role Prompting","created":"2025-08-30","cited_by_count":4,"area":"agents"},{"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":"2602.21428","title":"PSF-Med: Measuring and Explaining Paraphrase Sensitivity in Medical Vision Language Models","created":"2026-02-24","cited_by_count":4,"area":"mllm"},{"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":"2509.25873","title":"Lita: Light Agent Uncovers the Agentic Coding Capabilities of LLMs","created":"2025-09-30","cited_by_count":3,"area":"agents"},{"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":"2502.19622","title":"Weaker LLMs' Opinions Also Matter: Mixture of Opinions Enhances LLM's Mathematical Reasoning","created":"2025-02-26","cited_by_count":2,"area":"lr"},{"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":"2510.05124","title":"MADS: Multi-Agent Dialogue Simulation for Diverse Persuasion Data Generation","created":"2025-09-30","cited_by_count":2,"area":"agents"},{"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":"2607.01087","title":"Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software Engineering","created":"2026-07-01","cited_by_count":2,"area":"agents"},{"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":"2412.08307","title":"Investigating the Scaling Effect of Instruction Templates for Training Multimodal Language Model","created":"2024-12-11","cited_by_count":1,"area":"mllm"},{"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":"2505.13448","title":"CIE: Controlling Language Model Text Generations Using Continuous Signals","created":"2025-05-19","cited_by_count":1,"area":"alignment"},{"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":"2508.19093","title":"Retrieval-Augmented Generation for Natural Language Art Provenance Searches in the Getty Provenance Index","created":"2025-08-26","cited_by_count":1,"area":"rag"},{"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":"2602.00238","title":"DIVERGE: Diversity-Enhanced RAG for Open-Ended Information Seeking","created":"2026-01-30","cited_by_count":1,"area":"rag"},{"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":"2603.16210","title":"MOSAIC: Composable Safety Alignment with Modular Control Tokens","created":"2026-03-17","cited_by_count":1,"area":"alignment"},{"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":"2605.00326","title":"Prompt-Induced Score Variance in Zero-Shot Binary Vision-Language Safety Classification","created":"2026-05-01","cited_by_count":1,"area":"mllm"},{"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":"2605.21781","title":"Reflective Prompt Tuning through Language Model Function-Calling","created":"2026-05-20","cited_by_count":1,"area":"agents"},{"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":"2503.21840","title":"Vision Language Models versus Machine Learning Models Performance on Polyp Detection and Classification in Colonoscopy Images","created":"2025-03-27","cited_by_count":0,"area":"mllm"},{"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":"2507.13761","title":"Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models","created":"2025-07-18","cited_by_count":0,"area":"mllm"},{"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}],"next_cursor":"100"}