{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939},{"id":"2412.08905","title":"Phi-4 Technical Report","created":"2024-12-12","cited_by_count":711},{"id":"2009.10297","title":"CodeBLEU: a Method for Automatic Evaluation of Code Synthesis","created":"2020-09-22","cited_by_count":479},{"id":"2405.01535","title":"Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models","created":"2024-05-02","cited_by_count":446},{"id":"2207.10397","title":"CodeT: Code Generation with Generated Tests","created":"2022-07-21","cited_by_count":384},{"id":"2310.17631","title":"JudgeLM: Fine-tuned Large Language Models are Scalable Judges","created":"2023-10-26","cited_by_count":367},{"id":"2502.03373","title":"Demystifying Long Chain-of-Thought Reasoning in LLMs","created":"2025-02-05","cited_by_count":326},{"id":"2402.10669","title":"Humans or LLMs as the Judge? A Study on Judgement Biases","created":"2024-02-16","cited_by_count":323},{"id":"2410.12784","title":"JudgeBench: A Benchmark for Evaluating LLM-based Judges","created":"2024-10-16","cited_by_count":318},{"id":"2306.05087","title":"PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization","created":"2023-06-08","cited_by_count":316},{"id":"2306.06031","title":"FinGPT: Open-Source Financial Large Language Models","created":"2023-06-09","cited_by_count":253},{"id":"2410.16184","title":"RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style","created":"2024-10-21","cited_by_count":176},{"id":"2310.05470","title":"Generative Judge for Evaluating Alignment","created":"2023-10-09","cited_by_count":169},{"id":"2505.02387","title":"RM-R1: Reward Modeling as Reasoning","created":"2025-05-05","cited_by_count":154},{"id":"2407.00215","title":"LLM Critics Help Catch LLM Bugs","created":"2024-06-28","cited_by_count":147},{"id":"2406.12952","title":"SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents","created":"2024-06-18","cited_by_count":133},{"id":"2303.06689","title":"Self-planning Code Generation with Large Language Models","created":"2023-03-12","cited_by_count":124},{"id":"2308.06782","title":"PentestGPT: An LLM-empowered Automatic Penetration Testing Tool","created":"2023-08-13","cited_by_count":97},{"id":"2502.01718","title":"ACECODER: Acing Coder RL via Automated Test-Case Synthesis","created":"2025-02-03","cited_by_count":93},{"id":"2410.14872","title":"How to Evaluate Reward Models for RLHF","created":"2024-10-18","cited_by_count":88},{"id":"2505.16400","title":"AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning","created":"2025-05-22","cited_by_count":87},{"id":"2402.09171","title":"Automated Unit Test Improvement using Large Language Models at Meta","created":"2024-02-14","cited_by_count":75},{"id":"2408.02666","title":"Self-Taught Evaluators","created":"2024-08-05","cited_by_count":72},{"id":"2502.06193","title":"Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering","created":"2025-02-10","cited_by_count":67},{"id":"2311.18702","title":"CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation","created":"2023-11-30","cited_by_count":66},{"id":"2410.09893","title":"RMB: Comprehensively Benchmarking Reward Models in LLM Alignment","created":"2024-10-13","cited_by_count":61},{"id":"2403.09032","title":"CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences","created":"2024-03-14","cited_by_count":57},{"id":"2304.14317","title":"ICE-Score: Instructing Large Language Models to Evaluate Code","created":"2023-04-27","cited_by_count":52},{"id":"2405.17503","title":"Code Repair with LLMs gives an Exploration-Exploitation Tradeoff","created":"2024-05-26","cited_by_count":51},{"id":"2501.14723","title":"CodeMonkeys: Scaling Test-Time Compute for Software Engineering","created":"2025-01-24","cited_by_count":51},{"id":"2506.05817","title":"CodeContests+: High-Quality Test Case Generation for Competitive Programming","created":"2025-06-06","cited_by_count":46},{"id":"2312.15407","title":"A Comprehensive Analysis of the Effectiveness of Large Language Models as Automatic Dialogue Evaluators","created":"2023-12-24","cited_by_count":45},{"id":"2410.02184","title":"CodeJudge: Evaluating Code Generation with Large Language Models","created":"2024-10-03","cited_by_count":44},{"id":"2504.15253","title":"Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators","created":"2025-04-21","cited_by_count":44},{"id":"2504.04953","title":"M-Prometheus: A Suite of Open Multilingual LLM Judges","created":"2025-04-07","cited_by_count":38},{"id":"2408.10718","title":"CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?","created":"2024-08-20","cited_by_count":30},{"id":"2401.09042","title":"LLMs for Relational Reasoning: How Far are We?","created":"2024-01-17","cited_by_count":21},{"id":"2505.16222","title":"Don't Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation","created":"2025-05-22","cited_by_count":18},{"id":"2503.02246","title":"From Code to Courtroom: LLMs as the New Software Judges","created":"2025-03-04","cited_by_count":16},{"id":"2305.12228","title":"Dynamic Transformers Provide a False Sense of Efficiency","created":"2023-05-20","cited_by_count":14},{"id":"2407.01927","title":"TTSlow: Slow Down Text-to-Speech with Efficiency Robustness Evaluations","created":"2024-07-02","cited_by_count":13},{"id":"2502.13820","title":"Scoring Verifiers: Evaluating Synthetic Verification for Code and Reasoning","created":"2025-02-19","cited_by_count":9},{"id":"2505.20854","title":"An LLM-as-Judge Metric for Bridging the Gap with Human Evaluation in SE Tasks","created":"2025-05-27","cited_by_count":5},{"id":"2505.19502","title":"CODE-DITING: A Reasoning-Based Metric for Functional Alignment in Code Evaluation","created":"2025-05-26","cited_by_count":2}],"next_cursor":null}