一句话：实证评估开源文档翻译现状与两个 LLM 的翻译能力，揭示语义翻译可行但结构保持不足。
开源社区虽有全球多元化贡献者，但仅有少数仓库提供英文以外的 ReadMe 或 CONTRIBUTING 等文档。LLM 在多种软件工程任务中表现出色，但其翻译混合自然语言、代码、URL 与 Markdown 的技术文档的能力尚不明确。本文对开源翻译活动及两个强大 LLM（OpenAI ChatGPT 4 与 Anthropic Claude）的翻译能力进行实证评估。结果发现翻译活动多为社区驱动，且在较大仓库中更为频繁；LLM 作为翻译器与评估器时能提供准确的语义翻译，但在保留文档结构与技术内容方面仍有困难。这些发现既展示了 LLM 辅助文档国际化的前景，也指出了挑战，为自动化 LLM 驱动的开源文档创建与维护奠定了基础。
While open source communities attract diverse contributors across the globe, only a few open source software repositories provide essential documentation, such as ReadMe or CONTRIBUTING files, in languages other than English. Recently, large language models (LLMs) have demonstrated remarkable capabilities in a variety of software engineering tasks. We have also seen advances in the use of LLMs for translations in other domains and contexts. Despite this progress, little is known regarding the capabilities of LLMs in translating open-source technical documentation, which is often a mixture of natural language, code, URLs, and markdown formatting. To better understand the need and potential for LLMs to support translation of technical documentation in open source, we conducted an empirical evaluation of translation activity and translation capabilities of two powerful large language models (OpenAI ChatGPT 4 and Anthropic Claude). We found that translation activity is often community-driven and most frequent in larger repositories. A comparison of LLM performance as translators and evaluators of technical documentation suggests LLMs can provide accurate semantic translations but may struggle preserving structure and technical content. These findings highlight both the promise and the challenges of LLM-assisted documentation internationalization and provide a foundation towards automated LLM-driven support for creating and maintaining open source documentation.
@inproceedings{paperbot11982,
title = {Towards Bridging Language Gaps in OSS with LLM-Driven Documentation Translation},
author = {Elijah Kayode Adejumo and Mariam Guizani and Fatemeh Vares and Brittany Johnson},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3786582.3786828}
}