{"total":44,"rows":[{"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":"2204.05999","title":"InCoder: A Generative Model for Code Infilling and Synthesis","created":"2022-04-12","cited_by_count":498,"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":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300,"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":"2212.09420","title":"Large Language Models Meet NL2Code: A Survey","created":"2022-12-19","cited_by_count":138,"area":null},{"id":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135,"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":"2212.09248","title":"Natural Language to Code Generation in Interactive Data Science Notebooks","created":"2022-12-19","cited_by_count":87,"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":"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":"2310.10628","title":"Data Contamination Through the Lens of Time","created":"2023-10-16","cited_by_count":40,"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":"2201.12901","title":"Training and Evaluating a Jupyter Notebook Data Science Assistant","created":"2022-01-30","cited_by_count":31,"area":null},{"id":"2412.10064","title":"Text2Cypher: Bridging Natural Language and Graph Databases","created":"2024-12-13","cited_by_count":30,"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":"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":"2403.04814","title":"Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks","created":"2024-03-07","cited_by_count":25,"area":null},{"id":"2402.08699","title":"Unsupervised Evaluation of Code LLMs with Round-Trip Correctness","created":"2024-02-13","cited_by_count":23,"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":"2406.12655","title":"Benchmarks and Metrics for Evaluations of Code Generation: A Critical Review","created":"2024-06-18","cited_by_count":20,"area":null},{"id":"2506.13832","title":"FrontendBench: A Benchmark for Evaluating LLMs on Front-End Development via Automatic Evaluation","created":"2025-06-16","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":"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":"2212.06008","title":"Who Evaluates the Evaluators? On Automatic Metrics for Assessing AI-based Offensive Code Generators","created":"2022-12-12","cited_by_count":11,"area":null},{"id":"2504.08734","title":"Towards an Understanding of Context Utilization in Code Intelligence","created":"2025-04-11","cited_by_count":10,"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":"2211.00818","title":"CodePAD: Sequence-based Code Generation with Pushdown Automaton","created":"2022-11-02","cited_by_count":7,"area":null},{"id":"2104.01002","title":"HAConvGNN: Hierarchical Attention Based Convolutional Graph Neural Network for Code Documentation Generation in Jupyter Notebooks","created":"2021-03-31","cited_by_count":6,"area":null},{"id":"2405.01580","title":"On the Limitations of Embedding Based Methods for Measuring Functional Correctness for Code Generation","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2409.18475","title":"Data Analysis in the Era of Generative AI","created":"2024-09-27","cited_by_count":6,"area":null},{"id":"2411.05830","title":"GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation Models","created":"2024-11-05","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":"2312.13876","title":"Capture the Flag: Uncovering Data Insights with Large Language Models","created":"2023-12-21","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":"2202.04847","title":"A Survey on Artificial Intelligence for Source Code: A Dialogue Systems Perspective","created":"2022-02-10","cited_by_count":3,"area":null},{"id":"2202.07806","title":"Code Generation for Unknown Libraries via Reading API Documentations","created":"2022-02-16","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":"2502.18726","title":"Deep-Bench: Deep Learning Benchmark Dataset for Code Generation","created":"2025-02-26","cited_by_count":3,"area":null},{"id":"2504.09249","title":"NoTeS-Bank: Benchmarking Neural Transcription and Search for Scientific Notes Understanding","created":"2025-04-12","cited_by_count":3,"area":null},{"id":"2303.03593","title":"ADELT: Transpilation Between Deep Learning Frameworks","created":"2023-03-07","cited_by_count":2,"area":null},{"id":"2403.11585","title":"Linguacodus: A Synergistic Framework for Transformative Code Generation in Machine Learning Pipelines","created":"2024-03-18","cited_by_count":0,"area":null}],"next_cursor":null}