并非所有语言都平等：多语言检索增强生成的洞见
Not All Languages are Equal: Insights into Multilingual Retrieval-Augmented Generation
AI总结：
该研究构建了含八种语言平行文本的Futurepedia基准，评估六个多语言RALM发现语言不平等现象，并针对单语提取、跨语言迁移、多语言选择三方面提出改进建议，为多语言检索增强生成研究提供洞见。
摘要：
检索增强语言模型（RALMs）通过整合外部文本资源拓宽了其知识范围。然而，全球知识的多语言特性要求RALMs能够处理多种语言，这一主题目前受到的研究关注有限。在本研究中，我们提出了Futurepedia（未来百科），这是一个精心构建的基准，包含八种代表性语言的平行文本。我们利用该基准评估了六个多语言RALM，以探究多语言RALM面临的挑战。实验结果揭示了语言不平等现象：1）高资源语言在单语知识提取任务中表现突出；2）印欧语系语言会促使RALMs直接从文档中提取答案，缓解了跨语言表达答案的难题；3）英语因RALMs的选择偏差而受益，在多语言知识选择中占据主导地位。基于这些发现，我们为改进多语言检索增强生成提供了建议。在单语知识提取方面，必须高度关注低资源语言翻译为高资源语言时产生的级联错误。在跨语言知识迁移中，鼓励RALMs从不同语言的文档中直接生成答案可提升迁移性能。在多语言知识选择方面，纳入更多非英语文档并调整英语文档的定位有助于缓解RALMs的选择偏差。通过全面实验，我们强调了多语言RALM固有的复杂性，并为未来研究提供了有价值的洞见。
英文摘要：
RALMs (Retrieval-Augmented Language Models) broaden their knowledge scope by incorporating external textual resources. However, the multilingual nature of global knowledge necessitates RALMs to handle diverse languages, a topic that has received limited research focus. In this work, we propose \textit{Futurepedia}, a carefully crafted benchmark containing parallel texts across eight representative languages. We evaluate six multilingual RALMs using our benchmark to explore the challenges of multilingual RALMs. Experimental results reveal linguistic inequalities: 1) high-resource languages stand out in Monolingual Knowledge Extraction; 2) Indo-European languages lead RALMs to provide answers directly from documents, alleviating the challenge of expressing answers across languages; 3) English benefits from RALMs' selection bias and speaks louder in multilingual knowledge selection. Based on these findings, we offer advice for improving multilingual Retrieval Augmented Generation. For monolingual knowledge extraction, careful attention must be paid to cascading errors from translating low-resource languages into high-resource ones. In cross-lingual knowledge transfer, encouraging RALMs to provide answers within documents in different languages can improve transfer performance. For multilingual knowledge selection, incorporating more non-English documents and repositioning English documents can help mitigate RALMs' selection bias. Through comprehensive experiments, we underscore the complexities inherent in multilingual RALMs and offer valuable insights for future research.
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。
