一句话：提出 CodeGenLink，一个 VS Code 扩展，通过 LLM 搜索与相似性分析为 Copilot 生成代码推荐来源链接并标注许可证。
大语言模型（LLM）已广泛用于软件开发，但其生成代码缺乏来源信息，开发者难以评估可信度，并担心潜在的版权或许可证违规。本文提出 CodeGenLink，一个面向 GitHub Copilot 的 Visual Studio Code 扩展，旨在为自动生成代码推荐包含高度相似代码的链接，并在可能时指出其可能来源的许可证。该方法结合 LLM 及其网络搜索能力检索候选链接，再对生成代码与检索到的代码进行相似性分析，以过滤不相关结果。初步结果表明，CodeGenLink 能通过相似性分析有效过滤无关链接，并在信息可用时提供许可信息。该工具为 LLM 生成代码的溯源与许可证识别提供了一种集成于开发环境的实用方案。
Large Language Models (LLMs) are widely used in software development tasks nowadays. Unlike reusing code taken from the Web, for LLMs' generated code, developers are concerned about its lack of trustworthiness and possible copyright or licensing violations, due to the lack of code provenance information. This paper proposes CodeGenLink, a GitHub CoPilot extension for Visual Studio Code aimed at (i) suggesting links containing code very similar to automatically generated code, and (ii) whenever possible, indicating the license of the likely origin of the code. CodeGenLink retrieves candidate links by combining LLMs with their web search features and then performs similarity analysis between the generated and retrieved code. Preliminary results show that CodeGenLink effectively filters unrelated links via similarity analysis and provides licensing information when available.Tool URL: https://github.com/danielebifolco/CodeGenLinkTool Video: https://youtu.be/M6nqjBf_pw
DOI 原文 ·
@inproceedings{paperbot9211,
title = {CodeGenLink: A Tool to Find the Likely Origin and License of Automatically Generated Code},
author = {Daniele Bifolco and Guido Annicchiarico and Pierluigi Barbiero and Massimiliano Di Penta and Fiorella Zampetti},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00358}
}