{"total":46,"rows":[{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120,"area":null},{"id":"2406.11939","title":"From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline","created":"2024-06-17","cited_by_count":500,"area":null},{"id":"2502.01534","title":"Preference Leakage: A Contamination Problem in LLM-as-a-judge","created":"2025-02-03","cited_by_count":125,"area":null},{"id":"2407.10457","title":"The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism","created":"2024-07-15","cited_by_count":116,"area":null},{"id":"2407.04069","title":"A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations","created":"2024-07-04","cited_by_count":85,"area":null},{"id":"2503.21248","title":"ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition","created":"2025-03-27","cited_by_count":66,"area":null},{"id":"2409.15254","title":"Archon: An Architecture Search Framework for Inference-Time Techniques","created":"2024-09-23","cited_by_count":60,"area":null},{"id":"2410.07137","title":"Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates","created":"2024-10-09","cited_by_count":45,"area":null},{"id":"2502.03261","title":"CARROT: A Cost Aware Rate Optimal Router","created":"2025-02-05","cited_by_count":39,"area":null},{"id":"2503.05142","title":"RocketEval: Efficient Automated LLM Evaluation via Grading Checklist","created":"2025-03-07","cited_by_count":39,"area":null},{"id":"2509.11106","title":"Fluid Language Model Benchmarking","created":"2025-09-14","cited_by_count":35,"area":null},{"id":"2410.14826","title":"SPRIG: Improving Large Language Model Performance by System Prompt Optimization","created":"2024-10-18","cited_by_count":29,"area":null},{"id":"2505.11855","title":"When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research","created":"2025-05-17","cited_by_count":26,"area":null},{"id":"2409.03563","title":"100 instances is all you need: predicting the success of a new LLM on unseen data by testing on a few instances","created":"2024-09-05","cited_by_count":24,"area":null},{"id":"2501.18251","title":"How to Select Datapoints for Efficient Human Evaluation of NLG Models?","created":"2025-01-30","cited_by_count":23,"area":null},{"id":"2410.20245","title":"Improving Model Evaluation using SMART Filtering of Benchmark Datasets","created":"2024-10-26","cited_by_count":21,"area":null},{"id":"2502.01523","title":"CondAmbigQA: A Benchmark and Dataset for Conditional Ambiguous Question Answering","created":"2025-02-03","cited_by_count":15,"area":null},{"id":"2503.16402","title":"The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination","created":"2025-03-20","cited_by_count":15,"area":null},{"id":"2510.09869","title":"NarraBench: A Comprehensive Framework for Narrative Benchmarking","created":"2025-10-10","cited_by_count":13,"area":null},{"id":"2501.17178","title":"Tuning LLM Judge Design Decisions for 1/1000 of the Cost","created":"2025-01-24","cited_by_count":11,"area":null},{"id":"2508.06482","title":"Post-training for Efficient Communication via Convention Formation","created":"2025-08-08","cited_by_count":7,"area":null},{"id":"2410.13754","title":"MixEval-X: Any-to-Any Evaluations from Real-World Data Mixtures","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2505.17613","title":"MMMG: a Comprehensive and Reliable Benchmark for Multitask Multimodal Generation","created":"2025-05-23","cited_by_count":6,"area":null},{"id":"2508.10175","title":"Estimating Machine Translation Difficulty","created":"2025-08-13","cited_by_count":6,"area":null},{"id":"2505.02550","title":"Bielik v3 Small: Technical Report","created":"2025-05-05","cited_by_count":5,"area":null},{"id":"2509.21051","title":"When Instructions Multiply: Measuring and Estimating LLM Capabilities of Multiple Instructions Following","created":"2025-09-25","cited_by_count":5,"area":null},{"id":"2412.14471","title":"Why We Build Local Large Language Models: An Observational Analysis from 35 Japanese and Multilingual LLMs","created":"2024-12-19","cited_by_count":4,"area":null},{"id":"2505.12808","title":"Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models","created":"2025-05-19","cited_by_count":4,"area":null},{"id":"2409.00696","title":"Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation","created":"2024-09-01","cited_by_count":3,"area":null},{"id":"2506.00482","title":"Benchmarks Are Not Atomic: Composition-Aware LLM Evaluation using BenchHub","created":"2025-05-31","cited_by_count":3,"area":null},{"id":"2506.04142","title":"Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2601.06220","title":"Breaking Model Lock-in: Cost-Efficient Zero-Shot LLM Routing via a Universal Latent Space","created":"2026-01-09","cited_by_count":3,"area":null},{"id":"2606.24020","title":"You Don't Need to Run Every Eval","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2410.23331","title":"Can Models Help Us Create Better Models? Evaluating LLMs as Data Scientists","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2412.04947","title":"C$^2$LEVA: Toward Comprehensive and Contamination-Free Language Model Evaluation","created":"2024-12-06","cited_by_count":2,"area":null},{"id":"2505.02410","title":"Bielik 11B v2 Technical Report","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2505.06698","title":"SCAN: Structured Capability Assessment and Navigation for LLMs","created":"2025-05-10","cited_by_count":2,"area":null},{"id":"2505.14818","title":"WebNovelBench: Placing LLM Novelists on the Web Novel Distribution","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2604.12911","title":"Round-Trip Translation Reveals What Frontier Multilingual Benchmarks Miss","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2608.02620","title":"JudgeArena: A Unified Framework for Reproducible LLM-Judge Evaluation","created":"2026-07-01","cited_by_count":2,"area":null},{"id":"2412.17365","title":"Boosting LLM via Learning from Data Iteratively and Selectively","created":"2024-12-23","cited_by_count":1,"area":null},{"id":"2503.03592","title":"English K_Quantization of LLMs Does Not Disproportionately Diminish Multilingual Performance","created":"2025-03-05","cited_by_count":1,"area":null},{"id":"2508.18646","title":"Beyond Benchmarks: LLM Evaluation with an Anthropomorphic and Lifecycle-oriented Roadmap","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2606.26429","title":"DualEval: Joint Model-Item Calibration for Unified LLM Evaluation","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2608.03437","title":"Dynamically Allocating Evaluation Effort for Model Ranking","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.17183","title":"Benchmarking the Benchmarks: Evaluating Automated Safety Benchmarks for Small Language Models","created":"2026-08-17","cited_by_count":1,"area":null}],"next_cursor":null}