{"total":263,"rows":[{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320,"area":null},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637,"area":null},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139,"area":"lr"},{"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,"area":null},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332,"area":"lr"},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988,"area":"lr"},{"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,"area":null},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902,"area":null},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744,"area":null},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658,"area":null},{"id":"2407.01489","title":"Agentless: Demystifying LLM-based Software Engineering Agents","created":"2024-07-01","cited_by_count":421,"area":"agents"},{"id":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366,"area":null},{"id":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300,"area":null},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2105.12655","title":"CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks","created":"2021-05-25","cited_by_count":200,"area":null},{"id":"2205.11491","title":"HyperTree Proof Search for Neural Theorem Proving","created":"2022-05-23","cited_by_count":197,"area":null},{"id":"2303.05510","title":"Planning with Large Language Models for Code Generation","created":"2023-03-09","cited_by_count":182,"area":null},{"id":"2210.14868","title":"Multi-lingual Evaluation of Code Generation Models","created":"2022-10-26","cited_by_count":159,"area":null},{"id":"2407.11511","title":"Multi-Step Reasoning with Large Language Models, a Survey","created":"2024-07-16","cited_by_count":143,"area":"lr"},{"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,"area":null},{"id":"2404.00971","title":"Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code","created":"2024-04-01","cited_by_count":107,"area":null},{"id":"2301.13816","title":"Execution-based Code Generation using Deep Reinforcement Learning","created":"2023-01-31","cited_by_count":99,"area":null},{"id":"2410.14684","title":"RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph","created":"2024-10-03","cited_by_count":91,"area":null},{"id":"2212.09248","title":"Natural Language to Code Generation in Interactive Data Science Notebooks","created":"2022-12-19","cited_by_count":87,"area":null},{"id":"2110.06773","title":"Leveraging Automated Unit Tests for Unsupervised Code Translation","created":"2021-10-13","cited_by_count":82,"area":null},{"id":"2407.07263","title":"Reuse, Don't Retrain: A Recipe for Continued Pretraining of Language Models","created":"2024-07-09","cited_by_count":72,"area":null},{"id":"2106.06600","title":"Break-It-Fix-It: Unsupervised Learning for Program Repair","created":"2021-06-11","cited_by_count":71,"area":null},{"id":"2102.07492","title":"DOBF: A Deobfuscation Pre-Training Objective for Programming Languages","created":"2021-02-15","cited_by_count":68,"area":null},{"id":"2402.01035","title":"Getting the most out of your tokenizer for pre-training and domain adaptation","created":"2024-02-01","cited_by_count":66,"area":null},{"id":"2402.02037","title":"EffiBench: Benchmarking the Efficiency of Automatically Generated Code","created":"2024-02-03","cited_by_count":64,"area":null},{"id":"2410.24198","title":"SelfCodeAlign: Self-Alignment for Code Generation","created":"2024-10-31","cited_by_count":62,"area":null},{"id":"2105.08645","title":"CoTexT: Multi-task Learning with Code-Text Transformer","created":"2021-05-18","cited_by_count":61,"area":null},{"id":"2504.04030","title":"OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs","created":"2025-04-05","cited_by_count":60,"area":null},{"id":"2108.11590","title":"AVATAR: A Parallel Corpus for Java-Python Program Translation","created":"2021-08-26","cited_by_count":59,"area":null},{"id":"2310.04951","title":"CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation","created":"2023-10-08","cited_by_count":57,"area":null},{"id":"2404.14646","title":"Exploring and Unleashing the Power of Large Language Models in Automated Code Translation","created":"2024-04-23","cited_by_count":57,"area":null},{"id":"2206.08474","title":"XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence","created":"2022-06-16","cited_by_count":56,"area":null},{"id":"2206.07585","title":"NatGen: Generative pre-training by \"Naturalizing\" source code","created":"2022-06-15","cited_by_count":54,"area":null},{"id":"2102.07952","title":"A Survey of Machine Learning for Computer Architecture and Systems","created":"2021-02-16","cited_by_count":53,"area":null},{"id":"2309.14345","title":"Bias Testing and Mitigation in LLM-based Code Generation","created":"2023-09-03","cited_by_count":53,"area":null},{"id":"2309.07062","title":"Large Language Models for Compiler Optimization","created":"2023-09-11","cited_by_count":52,"area":null},{"id":"2207.11280","title":"PanGu-Coder: Program Synthesis with Function-Level Language Modeling","created":"2022-07-22","cited_by_count":48,"area":null},{"id":"2202.04903","title":"Investigating Explainability of Generative AI for Code through Scenario-based Design","created":"2022-02-10","cited_by_count":47,"area":null},{"id":"2303.03004","title":"xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval","created":"2023-03-06","cited_by_count":47,"area":null},{"id":"2412.10133","title":"You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects","created":"2024-12-13","cited_by_count":47,"area":"agents"},{"id":"2303.11455","title":"Large Language Models and Simple, Stupid Bugs","created":"2023-03-20","cited_by_count":45,"area":null},{"id":"2306.02907","title":"SelfEvolve: A Code Evolution Framework via Large Language Models","created":"2023-06-05","cited_by_count":43,"area":null},{"id":"2207.03578","title":"Code Translation with Compiler Representations","created":"2022-06-30","cited_by_count":42,"area":null},{"id":"2105.12485","title":"TreeBERT: A Tree-Based Pre-Trained Model for Programming Language","created":"2021-05-26","cited_by_count":41,"area":null},{"id":"2207.11680","title":"No More Fine-Tuning? An Experimental Evaluation of Prompt Tuning in Code Intelligence","created":"2022-07-24","cited_by_count":41,"area":null},{"id":"2407.02524","title":"Meta Large Language Model Compiler: Foundation Models of Compiler Optimization","created":"2024-06-27","cited_by_count":39,"area":null},{"id":"2108.11308","title":"What do pre-trained code models know about code?","created":"2021-08-25","cited_by_count":36,"area":null},{"id":"2206.05239","title":"StructCoder: Structure-Aware Transformer for Code Generation","created":"2022-06-10","cited_by_count":34,"area":null},{"id":"2206.01962","title":"Formal Specifications from Natural Language","created":"2022-06-04","cited_by_count":33,"area":null},{"id":"2401.03003","title":"AST-T5: Structure-Aware Pretraining for Code Generation and Understanding","created":"2024-01-05","cited_by_count":33,"area":null},{"id":"2407.03321","title":"Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languages","created":"2024-07-03","cited_by_count":33,"area":null},{"id":"2112.00791","title":"Controlling Conditional Language Models without Catastrophic Forgetting","created":"2021-12-01","cited_by_count":32,"area":null},{"id":"2211.09374","title":"Execution-based Evaluation for Data Science Code Generation Models","created":"2022-11-17","cited_by_count":32,"area":null},{"id":"2302.01973","title":"Measuring The Impact Of Programming Language Distribution","created":"2023-02-03","cited_by_count":32,"area":null},{"id":"2307.02503","title":"Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Review","created":"2023-07-04","cited_by_count":32,"area":null},{"id":"2304.10423","title":"Fully Autonomous Programming with Large Language Models","created":"2023-04-20","cited_by_count":31,"area":null},{"id":"2204.09653","title":"On the Transferability of Pre-trained Language Models for Low-Resource Programming Languages","created":"2022-04-05","cited_by_count":30,"area":null},{"id":"2405.15189","title":"EffiLearner: Enhancing Efficiency of Generated Code via Self-Optimization","created":"2024-05-24","cited_by_count":30,"area":null},{"id":"2408.10718","title":"CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?","created":"2024-08-20","cited_by_count":30,"area":null},{"id":"2104.02443","title":"CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance Computing","created":"2021-04-06","cited_by_count":28,"area":null},{"id":"2305.12520","title":"SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly","created":"2023-05-21","cited_by_count":28,"area":null},{"id":"2409.04556","title":"How Does Code Pretraining Affect Language Model Task Performance?","created":"2024-09-06","cited_by_count":28,"area":null},{"id":"2410.21680","title":"Revisiting Reliability in Large-Scale Machine Learning Research Clusters","created":"2024-10-29","cited_by_count":28,"area":null},{"id":"2410.24117","title":"AlphaTrans: A Neuro-Symbolic Compositional Approach for Repository-Level Code Translation and Validation","created":"2024-10-31","cited_by_count":28,"area":null},{"id":"2505.13004","title":"EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code","created":"2025-05-19","cited_by_count":27,"area":null},{"id":"2105.04297","title":"How could Neural Networks understand Programs?","created":"2021-05-10","cited_by_count":26,"area":null},{"id":"2202.08975","title":"Probing Pretrained Models of Source Code","created":"2022-02-16","cited_by_count":26,"area":null},{"id":"2405.11430","title":"MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation","created":"2024-05-19","cited_by_count":26,"area":null},{"id":"2406.04693","title":"LLM-Vectorizer: LLM-based Verified Loop Vectorizer","created":"2024-06-07","cited_by_count":25,"area":null},{"id":"2105.14220","title":"CoDesc: A Large Code-Description Parallel Dataset","created":"2021-05-29","cited_by_count":23,"area":null},{"id":"2412.17744","title":"RepoTransBench: A Real-World Multilingual Benchmark for Repository-Level Code Translation","created":"2024-12-23","cited_by_count":23,"area":null},{"id":"2306.06755","title":"CoTran: An LLM-based Code Translator using Reinforcement Learning with Feedback from Compiler and Symbolic Execution","created":"2023-06-11","cited_by_count":22,"area":null},{"id":"2307.02435","title":"Exploring Continual Learning for Code Generation Models","created":"2023-07-05","cited_by_count":22,"area":null},{"id":"2309.17446","title":"L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models","created":"2023-09-29","cited_by_count":22,"area":null},{"id":"2311.12833","title":"HPC-GPT: Integrating Large Language Model for High-Performance Computing","created":"2023-10-03","cited_by_count":22,"area":null},{"id":"2401.00288","title":"Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit","created":"2023-12-30","cited_by_count":22,"area":null},{"id":"2205.11739","title":"Deep Learning Meets Software Engineering: A Survey on Pre-Trained Models of Source Code","created":"2022-05-24","cited_by_count":21,"area":null},{"id":"2301.05578","title":"Toward General Design Principles for Generative AI Applications","created":"2023-01-13","cited_by_count":21,"area":null},{"id":"2306.00029","title":"CodeTF: One-stop Transformer Library for State-of-the-art Code LLMs","created":"2023-05-31","cited_by_count":21,"area":null},{"id":"2305.06156","title":"The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation","created":"2023-05-09","cited_by_count":20,"area":null},{"id":"2407.07472","title":"Rectifier: Code Translation with Corrector via LLMs","created":"2024-07-10","cited_by_count":20,"area":null},{"id":"2405.04520","title":"NaturalCodeBench: Examining Coding Performance Mismatch on HumanEval and Natural User Prompts","created":"2024-05-07","cited_by_count":19,"area":null},{"id":"2410.20527","title":"CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming","created":"2024-10-27","cited_by_count":19,"area":null},{"id":"2508.04295","title":"EvoC2Rust: A Skeleton-guided Framework for Project-Level C-to-Rust Translation","created":"2025-08-06","cited_by_count":19,"area":null},{"id":"2107.11864","title":"Neural Circuit Synthesis from Specification Patterns","created":"2021-07-25","cited_by_count":17,"area":null},{"id":"2410.10209","title":"EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning","created":"2024-10-14","cited_by_count":17,"area":null},{"id":"2305.14129","title":"GrACE: Generation using Associated Code Edits","created":"2023-05-23","cited_by_count":16,"area":null},{"id":"2306.14583","title":"Exploring the Robustness of Large Language Models for Solving Programming Problems","created":"2023-06-26","cited_by_count":16,"area":null},{"id":"2411.01063","title":"InterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translation","created":"2024-11-01","cited_by_count":16,"area":null},{"id":"2412.14234","title":"Syzygy: Dual Code-Test C to (safe) Rust Translation using LLMs and Dynamic Analysis","created":"2024-12-18","cited_by_count":16,"area":null},{"id":"2311.04929","title":"An Interdisciplinary Outlook on Large Language Models for Scientific Research","created":"2023-11-03","cited_by_count":15,"area":null},{"id":"2502.06111","title":"CSR-Bench: Benchmarking LLM Agents in Deployment of Computer Science Research Repositories","created":"2025-02-10","cited_by_count":15,"area":"agents"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2606.28434","title":"SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agents","created":"2026-06-26","cited_by_count":15,"area":"agents"},{"id":"2210.16494","title":"Aligning Offline Metrics and Human Judgments of Value for Code Generation Models","created":"2022-10-29","cited_by_count":14,"area":null}],"next_cursor":"100"}