AI 中文总结
该研究针对RAG的检索与阅读两类失效模式，提出轻量级插件SANE，通过语义检索+LM选候选、蓝图引导证据提取实现稳定性能提升，且开销适度。
AI 中文摘要
检索增强生成（RAG）在语言模型（LM）系统中存在两类根本失效模式：检索失效与阅读失效。前者无法从外部语料库召回正确的信息片段，后者虽召回了正确信息却无法生成正确答案。部分方法针对检索失效采用结构化索引，但可能受限于固定结构的泛化能力；部分方法针对阅读失效在查询时进行结构化处理，但通常需要大量LM调用且高度依赖LM的能力。为此，我们提出Select-ANd-Extract（SANE），一种简单且有效的RAG插件。针对检索失效，我们用语义检索器召回大量候选，再利用LM基于候选摘要选择顶部候选，相比原检索器召回效果更好；针对阅读失效，我们执行蓝图引导的查询时证据提取，让生成式LM仅使用紧凑结构化的关键信息，从而更好地推理。实验结果证实，SANE带来了稳定提升，仅引入适度的额外开销。作为RAG的轻量级插件，SANE为更复杂的方法提供了简单替代方案，表明高性能RAG框架无需过度复杂。
英文摘要
Retrieval-augmented generation (RAG) for language model (LM) systems fundamentally has two failure modes: retrieval failure and reading failure. The former fails to recall the right pieces of information from the external corpus, and the latter fails to produce the correct answer although the right information is retrieved. Some methods perform structured indexing for retrieval failure, but may suffer from limited generalization of the fixed structures. Some methods perform query-time structuring for reading failure, but typically require a lot of LM calls and rely heavily on the LM's capability. To this end, we propose Select-ANd-Extract (SANE), a simple yet effective plugin for RAG. For the retrieval failure, we retrieve a wide set of candidates with a semantic retriever, and leverage the LM to select the top candidates based on their synopses, which yields better recall than the original retriever. For the reading failure, we perform blueprint-guided query-time evidence extraction, which allows the generator LM to use only compact and structured key information so that it can perform better reasoning. Empirical results confirm that SANE brings solid improvements, while only introducing modest extra overhead. As a lightweight plugin for RAG, SANE offers a simple alternative to heavier approaches, and suggests a high-performance RAG framework need not be overly complex.
CommentsPre-print
