{"total":565,"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":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373,"area":null},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2407.21787","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","created":"2024-07-31","cited_by_count":991,"area":null},{"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,"area":null},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546,"area":null},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525,"area":null},{"id":"2501.14249","title":"Humanity's Last Exam","created":"2025-01-24","cited_by_count":491,"area":null},{"id":"2211.11501","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","created":"2022-11-18","cited_by_count":452,"area":null},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399,"area":null},{"id":"2207.10397","title":"CodeT: Code Generation with Generated Tests","created":"2022-07-21","cited_by_count":384,"area":null},{"id":"2303.12570","title":"RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation","created":"2023-03-22","cited_by_count":367,"area":null},{"id":"2404.19737","title":"Better & Faster Large Language Models via Multi-token Prediction","created":"2024-04-30","cited_by_count":360,"area":null},{"id":"2211.15533","title":"The Stack: 3 TB of permissively licensed source code","created":"2022-11-20","cited_by_count":359,"area":null},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358,"area":null},{"id":"2307.12856","title":"A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis","created":"2023-07-24","cited_by_count":353,"area":null},{"id":"2305.07922","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","created":"2023-05-13","cited_by_count":333,"area":null},{"id":"2303.17568","title":"CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X","created":"2023-03-30","cited_by_count":300,"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":"2509.16941","title":"SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?","created":"2025-09-21","cited_by_count":279,"area":null},{"id":"2302.05733","title":"Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks","created":"2023-02-11","cited_by_count":278,"area":null},{"id":"2312.02120","title":"Magicoder: Empowering Code Generation with OSS-Instruct","created":"2023-12-04","cited_by_count":256,"area":null},{"id":"2309.07544","title":"VerilogEval: Evaluating Large Language Models for Verilog Code Generation","created":"2023-09-14","cited_by_count":252,"area":null},{"id":"2306.14898","title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback","created":"2023-06-26","cited_by_count":238,"area":null},{"id":"2410.03859","title":"SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?","created":"2024-10-04","cited_by_count":203,"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":"2306.09896","title":"Is Self-Repair a Silver Bullet for Code Generation?","created":"2023-06-16","cited_by_count":197,"area":null},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189,"area":null},{"id":"2310.11248","title":"CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion","created":"2023-10-17","cited_by_count":183,"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":"2407.13168","title":"SciCode: A Research Coding Benchmark Curated by Scientists","created":"2024-07-18","cited_by_count":178,"area":null},{"id":"2301.03988","title":"SantaCoder: don't reach for the stars!","created":"2023-01-09","cited_by_count":170,"area":null},{"id":"2307.00184","title":"Personality Traits in Large Language Models","created":"2023-07-01","cited_by_count":169,"area":null},{"id":"2308.01861","title":"ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation","created":"2023-08-03","cited_by_count":168,"area":null},{"id":"2312.14852","title":"TACO: Topics in Algorithmic COde generation dataset","created":"2023-12-22","cited_by_count":160,"area":null},{"id":"2210.14868","title":"Multi-lingual Evaluation of Code Generation Models","created":"2022-10-26","cited_by_count":159,"area":null},{"id":"2503.14499","title":"Measuring AI Ability to Complete Long Software Tasks","created":"2025-03-18","cited_by_count":156,"area":null},{"id":"2212.09420","title":"Large Language Models Meet NL2Code: A Survey","created":"2022-12-19","cited_by_count":138,"area":null},{"id":"2208.08227","title":"MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation","created":"2022-08-17","cited_by_count":136,"area":null},{"id":"2204.11454","title":"Natural Language to Code Translation with Execution","created":"2022-04-25","cited_by_count":124,"area":null},{"id":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121,"area":null},{"id":"2308.08833","title":"CMB: A Comprehensive Medical Benchmark in Chinese","created":"2023-08-17","cited_by_count":115,"area":null},{"id":"2307.04349","title":"RLTF: Reinforcement Learning from Unit Test Feedback","created":"2023-07-10","cited_by_count":114,"area":null},{"id":"2305.04087","title":"Self-Edit: Fault-Aware Code Editor for Code Generation","created":"2023-05-06","cited_by_count":111,"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":"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,"area":null},{"id":"2401.08500","title":"Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering","created":"2024-01-16","cited_by_count":103,"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":"2202.12299","title":"Capturing Failures of Large Language Models via Human Cognitive Biases","created":"2022-02-24","cited_by_count":98,"area":null},{"id":"2205.06537","title":"Productivity Assessment of Neural Code Completion","created":"2022-05-13","cited_by_count":98,"area":null},{"id":"2210.01478","title":"When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment","created":"2022-10-04","cited_by_count":93,"area":null},{"id":"2210.14306","title":"Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming","created":"2022-10-25","cited_by_count":91,"area":null},{"id":"2212.10481","title":"Execution-Based Evaluation for Open-Domain Code Generation","created":"2022-12-20","cited_by_count":91,"area":null},{"id":"2206.06888","title":"CERT: Continual Pre-Training on Sketches for Library-Oriented Code Generation","created":"2022-06-14","cited_by_count":87,"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":"2310.00658","title":"The Robots are Here: Navigating the Generative AI Revolution in Computing Education","created":"2023-10-01","cited_by_count":86,"area":null},{"id":"2402.16694","title":"HumanEval-XL: A Multilingual Code Generation Benchmark for Cross-lingual Natural Language Generalization","created":"2024-02-26","cited_by_count":86,"area":null},{"id":"2506.19823","title":"Persona Features Control Emergent Misalignment","created":"2025-06-24","cited_by_count":86,"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":"2211.16490","title":"Coder Reviewer Reranking for Code Generation","created":"2022-11-29","cited_by_count":84,"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":"2207.14502","title":"Language Models Can Teach Themselves to Program Better","created":"2022-07-29","cited_by_count":78,"area":null},{"id":"2506.18902","title":"jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval","created":"2025-06-23","cited_by_count":76,"area":null},{"id":"2308.10335","title":"Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generation","created":"2023-08-20","cited_by_count":73,"area":null},{"id":"2402.05099","title":"Hydragen: High-Throughput LLM Inference with Shared Prefixes","created":"2024-02-07","cited_by_count":73,"area":null},{"id":"2404.00599","title":"EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories","created":"2024-03-31","cited_by_count":72,"area":null},{"id":"2404.10952","title":"Can Language Models Solve Olympiad Programming?","created":"2024-04-16","cited_by_count":72,"area":null},{"id":"2405.19856","title":"DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories","created":"2024-05-30","cited_by_count":72,"area":null},{"id":"2310.15654","title":"A Survey on Detection of LLMs-Generated Content","created":"2023-10-24","cited_by_count":71,"area":null},{"id":"2504.17192","title":"Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning","created":"2025-04-24","cited_by_count":70,"area":null},{"id":"2310.17807","title":"Clover: Closed-Loop Verifiable Code Generation","created":"2023-10-26","cited_by_count":67,"area":null},{"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,"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":"2407.02883","title":"CoIR: A Comprehensive Benchmark for Code Information Retrieval Models","created":"2024-07-03","cited_by_count":60,"area":null},{"id":"2401.07078","title":"PUB: A Pragmatics Understanding Benchmark for Assessing LLMs' Pragmatics Capabilities","created":"2024-01-13","cited_by_count":59,"area":null},{"id":"2501.08200","title":"CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation","created":"2025-01-14","cited_by_count":59,"area":null},{"id":"2605.03546","title":"ProgramBench: Can Language Models Rebuild Programs From Scratch?","created":"2026-05-05","cited_by_count":59,"area":null},{"id":"2310.08992","title":"CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules","created":"2023-10-13","cited_by_count":58,"area":null},{"id":"2503.06680","title":"FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation","created":"2025-03-09","cited_by_count":58,"area":null},{"id":"2305.19308","title":"SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models","created":"2023-05-30","cited_by_count":57,"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":"2406.08467","title":"DafnyBench: A Benchmark for Formal Software Verification","created":"2024-06-12","cited_by_count":57,"area":null},{"id":"2303.10845","title":"PanGu-{\\Sigma}: Towards Trillion Parameter Language Model with Sparse Heterogeneous Computing","created":"2023-03-20","cited_by_count":56,"area":null},{"id":"2210.17236","title":"When Language Model Meets Private Library","created":"2022-10-31","cited_by_count":54,"area":null},{"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,"area":null},{"id":"2306.05783","title":"Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation","created":"2023-06-09","cited_by_count":52,"area":null},{"id":"2412.01769","title":"Commit0: Library Generation from Scratch","created":"2024-12-02","cited_by_count":52,"area":null},{"id":"2405.17503","title":"Code Repair with LLMs gives an Exploration-Exploitation Tradeoff","created":"2024-05-26","cited_by_count":51,"area":null},{"id":"2406.11612","title":"Long Code Arena: a Set of Benchmarks for Long-Context Code Models","created":"2024-06-17","cited_by_count":50,"area":null},{"id":"2310.03046","title":"EcoAssistant: Using LLM Assistant More Affordably and Accurately","created":"2023-10-03","cited_by_count":49,"area":null},{"id":"2310.19791","title":"LILO: Learning Interpretable Libraries by Compressing and Documenting Code","created":"2023-10-30","cited_by_count":49,"area":null},{"id":"2407.21579","title":"A Performance Study of LLM-Generated Code on Leetcode","created":"2024-07-31","cited_by_count":49,"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":"2405.19550","title":"Stress-Testing Capability Elicitation With Password-Locked Models","created":"2024-05-29","cited_by_count":46,"area":null},{"id":"2406.11912","title":"AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology","created":"2024-06-16","cited_by_count":46,"area":null}],"next_cursor":"100"}