多语言环境下的检索增强生成
Retrieval-augmented generation in multilingual settings
AI总结：
本文研究多语言环境下的检索增强生成（mRAG），覆盖13种语言，发现需任务特定提示工程和评估指标调整，并发布mRAG基线流水线代码。
摘要：
检索增强生成（RAG）最近已成为一种有前景的解决方案，用于将最新或领域特定知识融入大型语言模型（LLMs）并提升LLM的事实准确性，但目前主要仅在英语环境中进行研究。在本工作中，我们考虑了多语言环境下的RAG（mRAG），即用户查询和数据存储涵盖13种语言，并研究构建一个性能良好的mRAG流水线需要哪些组件以及需要做出哪些调整，该流水线可作为未来工作中的强基线。我们的研究结果强调，尽管已有高质量的开箱即用多语言检索器和生成器，仍需进行任务特定的提示工程，以支持以用户语言进行生成。此外，当前的评估指标需要针对多语言环境进行调整，以考虑命名实体拼写的差异。未来工作中需要解决的主要局限性包括非拉丁字母语言中频繁的语码转换、偶发的流畅性错误、对所提供的文档的错误解读，或不相关的检索。我们在 https://github.com/naver/bergen 发布了由此得到的mRAG基线流水线的代码。
英文摘要：
Retrieval-augmented generation (RAG) has recently emerged as a promising solution for incorporating up-to-date or domain-specific knowledge into large language models (LLMs) and improving LLM factuality, but is predominantly studied in English-only settings. In this work, we consider RAG in the multilingual setting (mRAG), i.e. with user queries and the datastore in 13 languages, and investigate which components and with which adjustments are needed to build a well-performing mRAG pipeline, that can be used as a strong baseline in future works. Our findings highlight that despite the availability of high-quality off-the-shelf multilingual retrievers and generators, task-specific prompt engineering is needed to enable generation in user languages. Moreover, current evaluation metrics need adjustments for multilingual setting, to account for variations in spelling named entities. The main limitations to be addressed in future works include frequent code-switching in non-Latin alphabet languages, occasional fluency errors, wrong reading of the provided documents, or irrelevant retrieval. We release the code for the resulting mRAG baseline pipeline at https://github.com/naver/bergen.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
