{"total":71,"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":"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":"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":"2204.05999","title":"InCoder: A Generative Model for Code Infilling and Synthesis","created":"2022-04-12","cited_by_count":498,"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":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366,"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":"2306.14898","title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback","created":"2023-06-26","cited_by_count":238,"area":null},{"id":"2206.15331","title":"GitHub Copilot AI pair programmer: Asset or Liability?","created":"2022-06-30","cited_by_count":152,"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":"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":"2207.11280","title":"PanGu-Coder: Program Synthesis with Function-Level Language Modeling","created":"2022-07-22","cited_by_count":48,"area":null},{"id":"2208.05446","title":"CoditT5: Pretraining for Source Code and Natural Language Editing","created":"2022-08-10","cited_by_count":45,"area":null},{"id":"2311.08588","title":"CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation","created":"2023-11-14","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":"2408.08313","title":"Can Large Language Models Understand Symbolic Graphics Programs?","created":"2024-08-15","cited_by_count":35,"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":"2201.12901","title":"Training and Evaluating a Jupyter Notebook Data Science Assistant","created":"2022-01-30","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":"2212.06742","title":"ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages","created":"2022-12-13","cited_by_count":29,"area":null},{"id":"2306.03438","title":"Large Language Models of Code Fail at Completing Code with Potential Bugs","created":"2023-06-06","cited_by_count":29,"area":null},{"id":"2305.00909","title":"Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation","created":"2023-04-28","cited_by_count":27,"area":null},{"id":"2111.07875","title":"Choose Your Programming Copilot: A Comparison of the Program Synthesis Performance of GitHub Copilot and Genetic Programming","created":"2021-11-15","cited_by_count":24,"area":null},{"id":"2310.05103","title":"Zero-Shot Detection of Machine-Generated Codes","created":"2023-10-08","cited_by_count":24,"area":null},{"id":"2105.14220","title":"CoDesc: A Large Code-Description Parallel Dataset","created":"2021-05-29","cited_by_count":23,"area":null},{"id":"2307.02435","title":"Exploring Continual Learning for Code Generation Models","created":"2023-07-05","cited_by_count":22,"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":"2105.09352","title":"DeepDebug: Fixing Python Bugs Using Stack Traces, Backtranslation, and Code Skeletons","created":"2021-05-19","cited_by_count":17,"area":null},{"id":"2109.08780","title":"Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy","created":"2021-09-17","cited_by_count":14,"area":null},{"id":"2208.10091","title":"Incorporating Domain Knowledge through Task Augmentation for Front-End JavaScript Code Generation","created":"2022-08-22","cited_by_count":11,"area":null},{"id":"2210.14494","title":"CS1QA: A Dataset for Assisting Code-based Question Answering in an Introductory Programming Course","created":"2022-10-26","cited_by_count":11,"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":"2409.02074","title":"RACONTEUR: A Knowledgeable, Insightful, and Portable LLM-Powered Shell Command Explainer","created":"2024-09-03","cited_by_count":9,"area":null},{"id":"2210.14473","title":"Benchmarking Language Models for Code Syntax Understanding","created":"2022-10-26","cited_by_count":8,"area":null},{"id":"2212.10754","title":"CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding","created":"2022-12-21","cited_by_count":7,"area":null},{"id":"2302.03499","title":"Exploring Data Augmentation for Code Generation Tasks","created":"2023-02-05","cited_by_count":7,"area":null},{"id":"2108.10168","title":"CGEMs: A Metric Model for Automatic Code Generation using GPT-3","created":"2021-08-23","cited_by_count":6,"area":null},{"id":"2206.13619","title":"DeepPERF: A Deep Learning-Based Approach For Improving Software Performance","created":"2022-06-27","cited_by_count":6,"area":null},{"id":"2103.13426","title":"Learning to Generate Code Comments from Class Hierarchies","created":"2021-03-24","cited_by_count":5,"area":null},{"id":"2109.00084","title":"Program Merge Conflict Resolution via Neural Transformers","created":"2021-08-31","cited_by_count":5,"area":null},{"id":"2305.04940","title":"The EarlyBIRD Catches the Bug: On Exploiting Early Layers of Encoder Models for More Efficient Code Classification","created":"2023-05-08","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":"2211.15395","title":"CodeExp: Explanatory Code Document Generation","created":"2022-11-25","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":"2205.11023","title":"AdaptivePaste: Code Adaptation through Learning Semantics-aware Variable Usage Representations","created":"2022-05-23","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":"2404.02933","title":"NL2KQL: From Natural Language to Kusto Query","created":"2024-04-03","cited_by_count":3,"area":null},{"id":"2412.08291","title":"Code LLMs: A Taxonomy-based Survey","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2109.12296","title":"Jointly Learning to Repair Code and Generate Commit Message","created":"2021-09-25","cited_by_count":2,"area":null},{"id":"2201.08810","title":"GAP-Gen: Guided Automatic Python Code Generation","created":"2022-01-19","cited_by_count":2,"area":null},{"id":"2208.13928","title":"Exploring and Evaluating Personalized Models for Code Generation","created":"2022-08-29","cited_by_count":2,"area":null},{"id":"2311.01825","title":"Large Language Models to the Rescue: Reducing the Complexity in Scientific Workflow Development Using ChatGPT","created":"2023-11-03","cited_by_count":2,"area":null},{"id":"2202.03055","title":"Enabling Automatic Repair of Source Code Vulnerabilities Using Data-Driven Methods","created":"2022-02-07","cited_by_count":1,"area":null},{"id":"2211.07842","title":"Evaluating How Fine-tuning on Bimodal Data Effects Code Generation","created":"2022-11-15","cited_by_count":1,"area":null},{"id":"2310.05178","title":"Optimizing Large Language Models to Expedite the Development of Smart Contracts","created":"2023-10-08","cited_by_count":1,"area":null},{"id":"2310.14209","title":"SUT: Active Defects Probing for Transcompiler Models","created":"2023-10-22","cited_by_count":1,"area":null},{"id":"2402.05783","title":"Text-to-Code Generation with Modality-relative Pre-training","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2406.07084","title":"Leveraging Large Language Models for Efficient Failure Analysis in Game Development","created":"2024-06-11","cited_by_count":1,"area":null},{"id":"2108.03322","title":"Distilling Transformers for Neural Cross-Domain Search","created":"2021-08-06","cited_by_count":0,"area":null},{"id":"2201.11252","title":"Semantic Code Classification for Automated Machine Learning","created":"2022-01-25","cited_by_count":0,"area":null},{"id":"2202.12107","title":"From Natural Language to Simulations: Applying GPT-3 Codex to Automate Simulation Modeling of Logistics Systems","created":"2022-02-24","cited_by_count":0,"area":null},{"id":"2203.10744","title":"Programming Language Agnostic Mining of Code and Language Pairs with Sequence Labeling Based Question Answering","created":"2022-03-21","cited_by_count":0,"area":null},{"id":"2204.12648","title":"Generating Examples From CLI Usage: Can Transformers Help?","created":"2022-04-27","cited_by_count":0,"area":null},{"id":"2304.08243","title":"Stochastic Code Generation","created":"2023-04-14","cited_by_count":0,"area":null},{"id":"2311.06453","title":"DocGen: Generating Detailed Parameter Docstrings in Python","created":"2023-11-11","cited_by_count":0,"area":null},{"id":"2505.14759","title":"LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language Models","created":"2025-05-20","cited_by_count":0,"area":null}],"next_cursor":null}