{"total":25,"rows":[{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927,"area":null},{"id":"2406.07358","title":"AI Sandbagging: Language Models can Strategically Underperform on Evaluations","created":"2024-06-11","cited_by_count":145,"area":null},{"id":"2311.09783","title":"Investigating Data Contamination in Modern Benchmarks for Large Language Models","created":"2023-11-16","cited_by_count":138,"area":null},{"id":"2309.16289","title":"LawBench: Benchmarking Legal Knowledge of Large Language Models","created":"2023-09-28","cited_by_count":117,"area":null},{"id":"2402.01763","title":"When Large Language Models Meet Vector Databases: A Survey","created":"2024-01-30","cited_by_count":39,"area":null},{"id":"2602.16763","title":"When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation","created":"2026-02-18","cited_by_count":33,"area":null},{"id":"2406.14644","title":"Unveiling the Spectrum of Data Contamination in Language Models: A Survey from Detection to Remediation","created":"2024-06-20","cited_by_count":30,"area":null},{"id":"2507.12466","title":"Language Models Improve When Pretraining Data Matches Target Tasks","created":"2025-07-16","cited_by_count":19,"area":null},{"id":"2404.08008","title":"Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy Competition","created":"2024-04-10","cited_by_count":18,"area":null},{"id":"2510.05197","title":"Efficient Prediction of Pass@k Scaling in Large Language Models","created":"2025-10-06","cited_by_count":16,"area":null},{"id":"2402.01909","title":"On Catastrophic Inheritance of Large Foundation Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2402.11894","title":"Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models","created":"2024-02-19","cited_by_count":15,"area":null},{"id":"2410.09247","title":"Benchmark Inflation: Revealing LLM Performance Gaps Using Retro-Holdouts","created":"2024-10-11","cited_by_count":14,"area":null},{"id":"2401.15545","title":"PPM: Automated Generation of Diverse Programming Problems for Benchmarking Code Generation Models","created":"2024-01-28","cited_by_count":8,"area":null},{"id":"2408.04556","title":"BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models","created":"2024-08-08","cited_by_count":7,"area":null},{"id":"2507.17747","title":"Pretraining on the Test Set Is No Longer All You Need: A Debate-Driven Approach to QA Benchmarks","created":"2025-07-23","cited_by_count":7,"area":null},{"id":"2405.11265","title":"EnviroExam: Benchmarking Environmental Science Knowledge of Large Language Models","created":"2024-05-18","cited_by_count":5,"area":null},{"id":"2504.16921","title":"IberBench: LLM Evaluation on Iberian Languages","created":"2025-04-23","cited_by_count":5,"area":null},{"id":"2311.02049","title":"Post Turing: Mapping the landscape of LLM Evaluation","created":"2023-11-03","cited_by_count":4,"area":null},{"id":"2502.18339","title":"Correlating and Predicting Human Evaluations of Language Models from Natural Language Processing Benchmarks","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2509.23963","title":"Evaluating the Robustness of Chinchilla Compute-Optimal Scaling","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2601.04301","title":"Quantifying the Effect of Test Set Contamination on Generative Evaluations","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2502.15226","title":"Understand User Opinions of Large Language Models via LLM-Powered In-the-Moment User Experience Interviews","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2405.19250","title":"Kotlin ML Pack: Technical Report","created":"2024-05-29","cited_by_count":0,"area":null},{"id":"2509.26242","title":"Finetune Once: Decoupling General & Domain Learning with Dynamic Boosted Annealing","created":"2025-09-30","cited_by_count":0,"area":null}],"next_cursor":null}