{"list":"other","total":54,"rows":[{"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":"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":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"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":"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":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"2109.00859","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","created":"2021-09-02","cited_by_count":906},{"id":"2203.13474","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","created":"2022-03-25","cited_by_count":885},{"id":"2306.08568","title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","created":"2023-06-14","cited_by_count":733},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"2306.11644","title":"Textbooks Are All You Need","created":"2023-06-20","cited_by_count":569},{"id":"2402.19173","title":"StarCoder 2 and The Stack v2: The Next Generation","created":"2024-02-29","cited_by_count":502},{"id":"2303.12570","title":"RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation","created":"2023-03-22","cited_by_count":367},{"id":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366},{"id":"2006.03511","title":"Unsupervised Translation of Programming Languages","created":"2020-06-05","cited_by_count":263},{"id":"2312.02120","title":"Magicoder: Empowering Code Generation with OSS-Instruct","created":"2023-12-04","cited_by_count":256},{"id":"2402.14658","title":"OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement","created":"2024-02-22","cited_by_count":247},{"id":"2403.17134","title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","created":"2024-03-25","cited_by_count":232},{"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":"2310.11248","title":"CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion","created":"2023-10-17","cited_by_count":183},{"id":"2312.14852","title":"TACO: Topics in Algorithmic COde generation dataset","created":"2023-12-22","cited_by_count":160},{"id":"2210.14868","title":"Multi-lingual Evaluation of Code Generation Models","created":"2022-10-26","cited_by_count":159},{"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":"2406.12952","title":"SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents","created":"2024-06-18","cited_by_count":133},{"id":"2411.04905","title":"OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models","created":"2024-11-07","cited_by_count":130},{"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":"2302.07867","title":"Learning Performance-Improving Code Edits","created":"2023-02-15","cited_by_count":106},{"id":"2502.12115","title":"SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?","created":"2025-02-17","cited_by_count":105},{"id":"2212.14834","title":"Large Language Models are Zero-Shot Fuzzers: Fuzzing Deep-Learning Libraries via Large Language Models","created":"2022-12-30","cited_by_count":103},{"id":"2206.02369","title":"Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation","created":"2022-06-06","cited_by_count":94},{"id":"2302.05020","title":"Impact of Code Language Models on Automated Program Repair","created":"2023-02-10","cited_by_count":85},{"id":"2207.08281","title":"Less Training, More Repairing Please: Revisiting Automated Program Repair via Zero-shot Learning","created":"2022-07-17","cited_by_count":76},{"id":"2410.24198","title":"SelfCodeAlign: Self-Alignment for Code Generation","created":"2024-10-31","cited_by_count":62},{"id":"2108.11590","title":"AVATAR: A Parallel Corpus for Java-Python Program Translation","created":"2021-08-26","cited_by_count":59},{"id":"2309.00608","title":"Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair","created":"2023-09-01","cited_by_count":55},{"id":"2403.10059","title":"Repoformer: Selective Retrieval for Repository-Level Code Completion","created":"2024-03-15","cited_by_count":55},{"id":"2309.07062","title":"Large Language Models for Compiler Optimization","created":"2023-09-11","cited_by_count":52},{"id":"2312.14187","title":"WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning","created":"2023-12-20","cited_by_count":42},{"id":"2310.00297","title":"Understanding In-Context Learning from Repetitions","created":"2023-09-30","cited_by_count":29},{"id":"2407.21077","title":"Genetic Instruct: Scaling up Synthetic Generation of Coding Instructions for Large Language Models","created":"2024-07-29","cited_by_count":19},{"id":"2206.07796","title":"FixEval: Execution-based Evaluation of Program Fixes for Programming Problems","created":"2022-06-15","cited_by_count":17},{"id":"2205.11116","title":"Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languages","created":"2022-05-23","cited_by_count":12},{"id":"2502.13820","title":"Scoring Verifiers: Evaluating Synthetic Verification for Code and Reasoning","created":"2025-02-19","cited_by_count":9}],"next_cursor":null}