{"total":87,"rows":[{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637,"area":null},{"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":"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":"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":"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":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366,"area":null},{"id":"2203.03850","title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation","created":"2022-03-08","cited_by_count":361,"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":"2504.02605","title":"Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving","created":"2025-04-03","cited_by_count":171,"area":null},{"id":"2301.03988","title":"SantaCoder: don't reach for the stars!","created":"2023-01-09","cited_by_count":170,"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":"2207.05987","title":"DocPrompting: Generating Code by Retrieving the Docs","created":"2022-07-13","cited_by_count":153,"area":null},{"id":"2402.06954","title":"OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning","created":"2024-02-10","cited_by_count":128,"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":"2211.16490","title":"Coder Reviewer Reranking for Code Generation","created":"2022-11-29","cited_by_count":84,"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":"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":"2308.00675","title":"Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models","created":"2023-08-01","cited_by_count":68,"area":null},{"id":"2208.03133","title":"Out of the BLEU: how should we assess quality of the Code Generation models?","created":"2022-08-05","cited_by_count":65,"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":"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":"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":"2405.18653","title":"Recent Advances of Foundation Language Models-based Continual Learning: A Survey","created":"2024-05-28","cited_by_count":46,"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":"2310.09748","title":"Large Language Model-Aware In-Context Learning for Code Generation","created":"2023-10-15","cited_by_count":43,"area":null},{"id":"2203.08388","title":"MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages","created":"2022-03-16","cited_by_count":41,"area":null},{"id":"2311.00889","title":"SALLM: Security Assessment of Generated Code","created":"2023-11-01","cited_by_count":39,"area":null},{"id":"2502.06215","title":"LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks","created":"2025-02-10","cited_by_count":37,"area":null},{"id":"2405.02213","title":"Automatic Programming: Large Language Models and Beyond","created":"2024-05-03","cited_by_count":36,"area":null},{"id":"2408.14354","title":"SWE-bench-java: A GitHub Issue Resolving Benchmark for Java","created":"2024-08-26","cited_by_count":34,"area":null},{"id":"2410.22821","title":"EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations","created":"2024-10-30","cited_by_count":34,"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":"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":"2410.15037","title":"mHumanEval -- A Multilingual Benchmark to Evaluate Large Language Models for Code Generation","created":"2024-10-19","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":"2403.16443","title":"CodeS: Natural Language to Code Repository via Multi-Layer Sketch","created":"2024-03-25","cited_by_count":28,"area":null},{"id":"2407.02395","title":"Toward Secure Code Generation: Bridging Correctness and Security via Task-Adaptive Vulnerability Modeling and Execution-Based Benchmarking","created":"2024-07-02","cited_by_count":27,"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":"2401.00288","title":"Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit","created":"2023-12-30","cited_by_count":22,"area":null},{"id":"2406.11927","title":"On the Impacts of Contexts on Repository-Level Code Generation","created":"2024-06-17","cited_by_count":22,"area":null},{"id":"2304.05216","title":"Towards Efficient Fine-tuning of Pre-trained Code Models: An Experimental Study and Beyond","created":"2023-04-11","cited_by_count":20,"area":null},{"id":"2406.12655","title":"Benchmarks and Metrics for Evaluations of Code Generation: A Critical Review","created":"2024-06-18","cited_by_count":20,"area":null},{"id":"2212.09885","title":"Python Code Generation by Asking Clarification Questions","created":"2022-12-19","cited_by_count":17,"area":null},{"id":"2408.09121","title":"Selective Prompt Anchoring for Code Generation","created":"2024-08-17","cited_by_count":16,"area":null},{"id":"2310.16263","title":"Enhancing Large Language Models for Secure Code Generation: A Dataset-driven Study on Vulnerability Mitigation","created":"2023-10-25","cited_by_count":15,"area":null},{"id":"2212.10079","title":"A Survey on Pretrained Language Models for Neural Code Intelligence","created":"2022-12-20","cited_by_count":13,"area":null},{"id":"2412.18573","title":"Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark","created":"2024-12-24","cited_by_count":13,"area":null},{"id":"2503.13733","title":"CoDet-M4: Detecting Machine-Generated Code in Multi-Lingual, Multi-Generator and Multi-Domain Settings","created":"2025-03-17","cited_by_count":11,"area":null},{"id":"2406.12902","title":"JavaBench: A Benchmark of Object-Oriented Code Generation for Evaluating Large Language Models","created":"2024-06-10","cited_by_count":10,"area":null},{"id":"2502.13921","title":"Exploring Code Language Models for Automated HLS-based Hardware Generation: Benchmark, Infrastructure and Analysis","created":"2025-02-19","cited_by_count":10,"area":null},{"id":"2105.03317","title":"Toward Code Generation: A Survey and Lessons from Semantic Parsing","created":"2021-04-26","cited_by_count":8,"area":null},{"id":"2106.04447","title":"Reading StackOverflow Encourages Cheating: Adding Question Text Improves Extractive Code Generation","created":"2021-06-08","cited_by_count":8,"area":null},{"id":"2403.05188","title":"CommitBench: A Benchmark for Commit Message Generation","created":"2024-03-08","cited_by_count":8,"area":null},{"id":"2406.03283","title":"CATCODER: Repository-Level Code Generation with Relevant Code and Type Context","created":"2024-06-05","cited_by_count":8,"area":null},{"id":"2601.11895","title":"DevBench: A Realistic, Developer-Informed Benchmark for Code Generation Models","created":"2026-01-17","cited_by_count":8,"area":null},{"id":"2212.05901","title":"Parameter-Efficient Finetuning of Transformers for Source Code","created":"2022-12-12","cited_by_count":6,"area":null},{"id":"2504.19444","title":"Large Language Models are Qualified Benchmark Builders: Rebuilding Pre-Training Datasets for Advancing Code Intelligence Tasks","created":"2025-04-28","cited_by_count":6,"area":null},{"id":"2108.12144","title":"Lyra: A Benchmark for Turducken-Style Code Generation","created":"2021-08-27","cited_by_count":5,"area":null},{"id":"2108.05198","title":"Natural Language-Guided Programming","created":"2021-08-11","cited_by_count":4,"area":null},{"id":"2205.01293","title":"A Survey of Deep Learning Models for Structural Code Understanding","created":"2022-05-03","cited_by_count":4,"area":null},{"id":"2303.12869","title":"JaCoText: A Pretrained Model for Java Code-Text Generation","created":"2023-03-22","cited_by_count":4,"area":null},{"id":"2310.09690","title":"Configuration Validation with Large Language Models","created":"2023-10-15","cited_by_count":4,"area":null},{"id":"2312.04687","title":"LLM4TDD: Best Practices for Test Driven Development Using Large Language Models","created":"2023-12-07","cited_by_count":4,"area":null},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2203.03716","title":"GPT-based Open-Ended Knowledge Tracing","created":"2022-02-21","cited_by_count":3,"area":null},{"id":"2208.05596","title":"Finding Reusable Machine Learning Components to Build Programming Language Processing Pipelines","created":"2022-08-11","cited_by_count":3,"area":null},{"id":"2212.05773","title":"A Survey on Natural Language Processing for Programming","created":"2022-12-12","cited_by_count":3,"area":null},{"id":"2305.13504","title":"Neural Machine Translation for Code Generation","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2401.10716","title":"Structured Code Representations Enable Data-Efficient Adaptation of Code Language Models","created":"2024-01-19","cited_by_count":3,"area":null},{"id":"2402.13222","title":"RoCode: A Dataset for Measuring Code Intelligence from Problem Definitions in Romanian","created":"2024-02-20","cited_by_count":3,"area":null},{"id":"2409.13551","title":"Contextualized Data-Wrangling Code Generation in Computational Notebooks","created":"2024-09-20","cited_by_count":3,"area":null},{"id":"2504.15564","title":"OpenClassGen: A Large-Scale Corpus of Real-World Python Classes for LLM Research","created":"2025-04-22","cited_by_count":3,"area":null},{"id":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2306.06371","title":"A Comprehensive Review of State-of-The-Art Methods for Java Code Generation from Natural Language Text","created":"2023-06-10","cited_by_count":2,"area":null},{"id":"2403.10575","title":"Exploring Language Model's Code Generation Ability with Auxiliary Functions","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2502.12490","title":"UniGenCoder: Merging Seq2Seq and Seq2Tree Paradigms for Unified Code Generation","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2504.20673","title":"CoCo-Bench: A Comprehensive Code Benchmark For Multi-task Large Language Model Evaluation","created":"2025-04-29","cited_by_count":1,"area":null},{"id":"2505.20505","title":"Large Language Models for IT Automation Tasks: Are We There Yet?","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2601.04085","title":"CSSG: Measuring Code Similarity with Semantic Graphs","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2309.07429","title":"Semantic Parsing in Limited Resource Conditions","created":"2023-09-14","cited_by_count":0,"area":null},{"id":"2506.02791","title":"Contamination Means Overestimation? A Fine-Grained Empirical Study in Code Intelligence","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2605.12153","title":"CIDR: A Large-Scale Industrial Source Code Dataset for Software Engineering Research","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2607.16692","title":"Dependency-Guided Code Generation: Structured Matrix Decomposition and Consistency-Guided Refinement","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2609.03702","title":"Synthetic Semantic Supervision for Contrastive Code Representation Learning in Small Transformers: An Empirical Study","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":null}