让检索到的证据更熟悉模型，提升问答准确率
Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation
- 不依赖训练，通过增强证据与模型的熟悉度来压缩
- 在多个数据集上最高提升28.1%准确率，压缩率高
- 适合需要融合外部知识和自身记忆的生成任务
检索增强生成（RAG）通过从外部源检索证据来提升大语言模型（LM）性能。然而，当涉及多条证据时，不一致或无关信息常干扰模型判断。尽管用压缩模型处理证据可缓解此问题，但压缩后的证据仍可能对目标模型不熟悉，导致利用率下降。本文提出FaviComp（熟悉度感知证据压缩），一种无需训练的新型压缩技术，使检索证据更贴近目标模型的参数化知识，实现两种知识的无缝融合。实验表明，FaviComp在多个开放域问答数据集上持续优于多数最新压缩基线，在保持高压缩率的同时，准确率最高提升28.1%。此外，验证了参数化与非参数化知识在压缩阶段的有效整合。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) improves large language models (LMs) by incorporating non-parametric knowledge through evidence retrieved from external sources. However, it often struggles to cope with inconsistent and irrelevant information that can distract the LM from its tasks, especially when multiple evidence pieces are required. While compressing the retrieved evidence with a compression model aims to address this issue, the compressed evidence may still be unfamiliar to the target model used for downstream tasks, potentially failing to utilize the evidence effectively. We propose FaviComp (Familarity-Aware Evidence Compression), a novel training-free evidence compression technique that makes retrieved evidence more familiar to the target model, while seamlessly integrating parametric knowledge from the model. Experimental results show that FaviComp consistently outperforms most recent evidence compression baselines across multiple open-domain QA datasets, improving accuracy by up to 28.1% while achieving high compression rates. Additionally, we demonstrate the effective integration of both parametric and non-parametric knowledge during evidence compression.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。