基于原子单元的问题检索用于企业级RAG
Question-Based Retrieval using Atomic Units for Enterprise RAG
AI总结：
本文提出将文档块分解为原子陈述并生成合成问题进行零样本稠密检索，以提升企业RAG的块召回率，实验表明该方法优于直接使用块检索，并能提高企业LLM的整体性能。
摘要：
企业检索增强生成（RAG）为将强大的大型语言模型（LLMs）与内部可能随时间变化的文档相结合，提供了一种高度灵活的框架。在RAG中，文档首先被分块。然后针对用户查询检索相关块，并将其作为上下文传递给合成器LLM以生成查询响应。然而，检索步骤可能会限制性能，因为错误的块可能导致合成器LLM生成错误响应。本工作应用标准稠密检索步骤的零样本自适应方法，以实现更准确的块召回。具体来说，首先将块分解为原子陈述。然后基于这些原子（以该块为上下文）生成一组合成问题。稠密检索涉及找到与用户查询最接近的一组合成问题及其关联块。研究发现，使用原子进行检索比使用块进行检索具有更高的召回率。使用基于原子生成的合成问题进行检索时，观察到进一步的性能提升。检索步骤中更高的召回率使得使用RAG流水线的企业LLM能够获得更高的性能。
英文摘要：
Enterprise retrieval augmented generation (RAG) offers a highly flexible framework for combining powerful large language models (LLMs) with internal, possibly temporally changing, documents. In RAG, documents are first chunked. Relevant chunks are then retrieved for a user query, which are passed as context to a synthesizer LLM to generate the query response. However, the retrieval step can limit performance, as incorrect chunks can lead the synthesizer LLM to generate a false response. This work applies a zero-shot adaptation of standard dense retrieval steps for more accurate chunk recall. Specifically, a chunk is first decomposed into atomic statements. A set of synthetic questions are then generated on these atoms (with the chunk as the context). Dense retrieval involves finding the closest set of synthetic questions, and associated chunks, to the user query. It is found that retrieval with the atoms leads to higher recall than retrieval with chunks. Further performance gain is observed with retrieval using the synthetic questions generated over the atoms. Higher recall at the retrieval step enables higher performance of the enterprise LLM using the RAG pipeline.
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。
