关于检索内容表示对RAG管道的影响
On the impact of retrieved content representations in RAG Pipelines
AI总结：
通过控制变量实验，研究检索文档的不同表示（选择、摘要、改写等）对RAG生成准确性的影响，发现答案保留是主要决定因素。
摘要：
检索增强生成（RAG）通过检索到的文档补充语言模型的输入，但大多数RAG管道继承了为人类读者设计的检索组件。当消费者是大型语言模型（LLM）而非人类时，检索内容应如何表示尚不清楚。最近的工作提出了对检索内容的转换，并识别了影响生成的属性，但每项工作仅孤立地考察单一转换或属性，未明确文档表示的哪些特征最重要。我们通过控制比较来解决这一问题：固定检索不变，仅改变检索文档的表示，将原始基线与其他十三种转换（涵盖选择、摘要和改写，包括查询相关和查询无关变体）进行比较。在这十四种表示中，我们测量了四个生成器的问答准确性，并对每种表示测量了答案保留：即已知包含答案的文档在转换后是否仍支持其答案。我们发现，答案保留是生成器准确性的主要决定因素；值得注意的是，当保留率高时，表示的措辞、结构、长度和查询相关性影响有限。这表明，先前工作中归因于特定机制的准确性提升，可能部分由这些机制保留答案内容的能力解释，而这种归因在未控制保留的情况下无法确定。
英文摘要：
Retrieval-Augmented Generation (RAG) supplements a language model's input with retrieved documents, yet most RAG pipelines inherit retrieval components designed for human readers. How retrieved content should be represented when the consumer is a large language model (LLM) rather than a human is less well understood. Recent work has proposed transformations of retrieved content and identified properties that affect generation, but each examines a single transformation or property in isolation, leaving open which features of a document's representation matter most. We address this with a controlled comparison: holding retrieval fixed, we vary only the representation of retrieved documents, comparing an original baseline against thirteen transformations spanning selection, summarisation, and reformulation, in query-dependent and query-independent variants. Across these fourteen representations we measure question-answering accuracy for four generators, and for each representation we also measure answer retention: whether a known answer-bearing document still supports its answer after transformation. We find that answer retention is the primary determinant of generator accuracy; notably, when retention is high, a representation's wording, structure, length, and query-dependence have limited effect. This suggests that accuracy gains attributed to specific mechanisms in prior work may be partly explained by how well those mechanisms preserve answer-bearing content, an attribution that cannot be settled without controlling for retention.
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。
