{"list":"other","total":60,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"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":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"1909.09436","title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search","created":"2019-09-20","cited_by_count":654},{"id":"2310.04406","title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","created":"2023-10-06","cited_by_count":574},{"id":"2308.08998","title":"Reinforced Self-Training (ReST) for Language Modeling","created":"2023-08-17","cited_by_count":500},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467},{"id":"2409.12917","title":"Training Language Models to Self-Correct via Reinforcement Learning","created":"2024-09-19","cited_by_count":426},{"id":"2207.10397","title":"CodeT: Code Generation with Generated Tests","created":"2022-07-21","cited_by_count":384},{"id":"2406.11931","title":"DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence","created":"2024-06-17","cited_by_count":331},{"id":"2401.07339","title":"CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges","created":"2024-01-14","cited_by_count":282},{"id":"2304.07590","title":"Self-collaboration Code Generation via ChatGPT","created":"2023-04-15","cited_by_count":258},{"id":"2402.14658","title":"OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement","created":"2024-02-22","cited_by_count":247},{"id":"2302.08468","title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","created":"2023-02-16","cited_by_count":239},{"id":"2403.17134","title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","created":"2024-03-25","cited_by_count":232},{"id":"2311.17311","title":"Universal Self-Consistency for Large Language Model Generation","created":"2023-11-29","cited_by_count":203},{"id":"2306.09896","title":"Is Self-Repair a Silver Bullet for Code Generation?","created":"2023-06-16","cited_by_count":197},{"id":"2302.06527","title":"An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation","created":"2023-02-13","cited_by_count":194},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189},{"id":"2303.05510","title":"Planning with Large Language Models for Code Generation","created":"2023-03-09","cited_by_count":182},{"id":"2210.14179","title":"Practical Program Repair in the Era of Large Pre-trained Language Models","created":"2022-10-25","cited_by_count":133},{"id":"2402.16906","title":"Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step","created":"2024-02-25","cited_by_count":127},{"id":"2304.00385","title":"Keep the Conversation Going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT","created":"2023-04-01","cited_by_count":125},{"id":"2312.04474","title":"Chain of Code: Reasoning with a Language Model-Augmented Code Emulator","created":"2023-12-07","cited_by_count":123},{"id":"2307.04349","title":"RLTF: Reinforcement Learning from Unit Test Feedback","created":"2023-07-10","cited_by_count":114},{"id":"2305.04087","title":"Self-Edit: Fault-Aware Code Editor for Code Generation","created":"2023-05-06","cited_by_count":111},{"id":"2401.04621","title":"DebugBench: Evaluating Debugging Capability of Large Language Models","created":"2024-01-09","cited_by_count":76},{"id":"2106.06600","title":"Break-It-Fix-It: Unsupervised Learning for Program Repair","created":"2021-06-11","cited_by_count":71},{"id":"2212.10561","title":"Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions","created":"2022-12-20","cited_by_count":64},{"id":"2404.14662","title":"NExT: Teaching Large Language Models to Reason about Code Execution","created":"2024-04-23","cited_by_count":63},{"id":"2407.06153","title":"What's Wrong with Your Code Generated by Large Language Models? An Extensive Study","created":"2024-07-08","cited_by_count":53},{"id":"2306.02907","title":"SelfEvolve: A Code Evolution Framework via Large Language Models","created":"2023-06-05","cited_by_count":43},{"id":"2403.18746","title":"CYCLE: Learning to Self-Refine the Code Generation","created":"2024-03-27","cited_by_count":42},{"id":"2301.13246","title":"Conversational Automated Program Repair","created":"2023-01-30","cited_by_count":41},{"id":"2405.18649","title":"LeDex: Training LLMs to Better Self-Debug and Explain Code","created":"2024-05-28","cited_by_count":40},{"id":"2007.08095","title":"Synthesize, Execute and Debug: Learning to Repair for Neural Program Synthesis","created":"2020-07-16","cited_by_count":39},{"id":"2404.11595","title":"A Deep Dive into Large Language Models for Automated Bug Localization and Repair","created":"2024-04-17","cited_by_count":39},{"id":"2305.00909","title":"Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation","created":"2023-04-28","cited_by_count":27},{"id":"2311.14904","title":"LLM-Assisted Code Cleaning For Training Accurate Code Generators","created":"2023-11-25","cited_by_count":27},{"id":"2401.06461","title":"Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human Programmers","created":"2024-01-12","cited_by_count":27},{"id":"2309.09308","title":"GAMMA: Revisiting Template-based Automated Program Repair via Mask Prediction","created":"2023-09-17","cited_by_count":23},{"id":"2407.20898","title":"ThinkRepair: Self-Directed Automated Program Repair","created":"2024-07-30","cited_by_count":23},{"id":"1812.07270","title":"AVATAR : Fixing Semantic Bugs with Fix Patterns of Static Analysis Violations","created":"2018-12-18","cited_by_count":22},{"id":"2403.01971","title":"ContrastRepair: Enhancing Conversation-Based Automated Program Repair via Contrastive Test Case Pairs","created":"2024-03-04","cited_by_count":19},{"id":"2311.07215","title":"Coffee: Boost Your Code LLMs by Fixing Bugs with Feedback","created":"2023-11-13","cited_by_count":15},{"id":"2401.05319","title":"Leveraging Print Debugging to Improve Code Generation in Large Language Models","created":"2024-01-10","cited_by_count":15},{"id":"2406.04604","title":"Learning Task Decomposition to Assist Humans in Competitive Programming","created":"2024-06-07","cited_by_count":14},{"id":"2308.14460","title":"STEAM: Simulating the InTeractive BEhavior of ProgrAMmers for Automatic Bug Fixing","created":"2023-08-28","cited_by_count":9}],"next_cursor":null}