{"total":23,"rows":[{"id":"2509.03730","title":"The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs","created":"2025-09-03","cited_by_count":36,"area":null},{"id":"2503.17181","title":"A Study of LLMs' Preferences for Libraries and Programming Languages","created":"2025-03-21","cited_by_count":20,"area":null},{"id":"2508.00408","title":"Benchmarking LLMs for Unit Test Generation from Real-World Functions","created":"2025-08-01","cited_by_count":8,"area":null},{"id":"2602.12413","title":"Soft Contamination Means Benchmarks Test Shallow Generalization","created":"2026-02-12","cited_by_count":8,"area":null},{"id":"2506.12376","title":"ConsistencyChecker: Tree-based Evaluation of LLM Generalization Capabilities","created":"2025-06-14","cited_by_count":5,"area":null},{"id":"2606.09401","title":"Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models","created":"2026-06-08","cited_by_count":4,"area":null},{"id":"2602.04296","title":"ProxyWar: Dynamic Assessment of LLM Code Generation in Game Arenas","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2507.16514","title":"The Ever-Evolving Science Exam","created":"2025-07-22","cited_by_count":2,"area":null},{"id":"2508.01203","title":"Importance Sampling is All You Need: Predict LLM's performance on new benchmark by reusing existing benchmark","created":"2025-08-02","cited_by_count":2,"area":null},{"id":"2508.17767","title":"ISACL: Internal State Analyzer for Copyrighted Training Data Leakage","created":"2025-08-25","cited_by_count":2,"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":"2509.18093","title":"SEQR: Secure and Efficient QR-based LoRA Routing","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2506.18213","title":"A Conceptual Framework for AI Capability Evaluations","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2508.16071","title":"From Benchmark Data To Applicable Program Repair: An Experience Report","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2508.20275","title":"A Systematic Review on the Generative AI Applications in Human Medical Genomics","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2509.22768","title":"ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2601.10926","title":"Selecting Language Models for Social Science: Start Small, Start Open, and Validate","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2604.21579","title":"A Metamorphic Testing Approach to Diagnosing Memorization in LLM-Based Program Repair","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2606.19149","title":"OpenAnt: LLM-Powered Vulnerability Discovery Through Code Decomposition, Adversarial Verification, and Dynamic Testing","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.19788","title":"CombEval: A Framework for Evaluating Combinatorial Counting in Large Language Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.29815","title":"SrDetection: A Self-Referential Framework for Data Leakage Detection in Code Large Language Models","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2608.00672","title":"From Chasing Ghosts to Missed Attacks: Perspectives and Perceptions of SOC Practitioners on LLM Integration, Risks, and Readiness","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2609.30360","title":"Cost-Aware Best-LLM Identification using Dueling Feedback","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}