mlsanityData to 7 Oct 2026

Automatic Code Documentation Generation Using GPT-3

arXiv 2209.02235 ↗First posted 6 Sep 2022cs.SEcited by 37

Not on the map. Why?

Abstract (arXiv)

Source code documentation is an important artifact for efficient software development. Code documentation could greatly benefit from automation since manual documentation is often labouring, resource and time-intensive. In this paper, we employed Codex for automatic code documentation creation. Codex is a GPT-3 based model pre-trained on both natural and programming languages. We find that Codex outperforms existing techniques even with basic settings like one-shot learning (i.e., providing only one example for training). Codex achieves an overall BLEU score of 20.6 for six different programming languages (11.2% improvement over earlier state-of-the-art techniques). Thus, Codex shows promise and warrants in-depth future studies for automatic code documentation generation to support diverse development tasks.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Sep 2022.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 10; 2024: 11; 2025: 6; 2026: 10.

37 papers.

Sort:

By area:

  1. 2023A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4cited by 81
  2. 2024RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generationcited by 69
  3. 2023A Comparative Analysis of Large Language Models for Code Documentation Generationcited by 24
  4. 2024Learning Agent-based Modeling with LLM Companions: Experiences of Novices and Experts Using ChatGPT & NetLogo Chatcited by 23
  5. 2024The Landscape and Challenges of HPC Research and LLMscited by 22
  6. 2024Performance-Aligned LLMs for Generating Fast Codecited by 20
  7. 2023From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscapecited by 18
  8. 2023From Commit Message Generation to History-Aware Commit Message Completioncited by 16
  9. 2023Autonomous Agents in Software Development: A Vision Papercited by 12
  10. 2023ChatGPT for PLC/DCS Control Logic Generationcited by 9
  11. 2023Multilingual Code Co-Evolution Using Large Language Modelscited by 9
  12. 2024VulnLLMEval: A Framework for Evaluating Large Language Models in Software Vulnerability Detection and Patchingcited by 9
25 more
  1. 2024Prompting and Fine-tuning Large Language Models for Automated Code Review Comment Generationcited by 7
  2. 2023Semantic Similarity Loss for Neural Source Code Summarizationcited by 5
  3. 2023Co-audit: tools to help humans double-check AI-generated contentcited by 5
  4. 2024ChatGPT Incorrectness Detection in Software Reviewscited by 5
  5. 2025Generative AI for Self-Adaptive Systems: State of the Art and Research Roadmapcited by 5
  6. 2026RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repaircited by 5
  7. 2025Evaluating the Effectiveness of LLMs in Fixing Maintainability Issues in Real-World Projectscited by 4
  8. 2024CodeCloak: A Method for Evaluating and Mitigating Code Leakage by LLM Code Assistantscited by 3
  9. 2024Mastering the Craft of Data Synthesis for CodeLLMscited by 3
  10. 2024MESIA: Understanding and Leveraging Supplementary Nature of Method-level Comments for Automatic Comment Generationcited by 2
  11. 2025Evaluating the Use of LLMs for Documentation to Code Traceabilitycited by 2
  12. 2026Evaluating Repository-level Software Documentation via Question Answering and Feature-Driven Developmentcited by 2
  13. 2024Assessing the Code Clone Detection Capability of Large Language Modelscited by 1
  14. 2025Impact of Comments on LLM Comprehension of Legacy Codecited by 1
  15. 2025SODBench: A Large Language Model Approach to Documenting Spreadsheet Operationscited by 1
  16. 2026Q-Bridge: Code Translation for Quantum Machine Learning via LLMscited by 1
  17. 2026Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentationcited by 1
  18. 2023Empowering Business Transformation: The Positive Impact and Ethical Considerations of Generative AI in Software Product Management -- A Systematic Literature Reviewcited by 0
  19. 2025Issue Retrieval and Verification Enhanced Supplementary Code Comment Generationcited by 0
  20. 2026Precision in Practice: Knowledge Guided Code Summarizing Grounded in Industrial Expectationscited by 0
  21. 2026Prompt-Driven Code Summarization: A Systematic Literature Reviewcited by 0
  22. 2026Benchmarked Yet Not Measured -- Generative AI Should be Evaluated Against Real-World Utilitycited by 0
  23. 2026The Illusion of Agentic Complexity in README.md Generation: Evaluating Single-Agent vs. Multi-Agent RAG Systemscited by 0
  24. 2026SAGE-Loop: Reliable Closed-Loop LLM-Driven AutoML with Trial-and-Correction and Adaptive Ensemblingcited by 0
  25. 2026Compact Documentation for Coding Agents: A Benchmark, an Optimizer, and Why It Does Not Transfercited by 0