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.

翻译：检索增强生成（RAG）通过从外部源检索证据并整合非参数化知识，从而改进大型语言模型（LM）。然而，当需要多份证据时，RAG常常难以处理不一致和无关的信息，这些信息可能会分散LM对其任务的注意力。虽然使用压缩模型对检索到的证据进行压缩旨在解决此问题，但压缩后的证据对于用于下游任务的目标模型而言可能仍然不熟悉，从而可能无法有效利用证据。我们提出了FaviComp（基于熟悉度的证据压缩），这是一种新颖的无训练证据压缩技术，它使检索到的证据对目标模型更为熟悉，同时无缝地整合了模型中的参数化知识。实验结果表明，在多个开放域QA数据集上，FaviComp持续优于最新的证据压缩基线方法，在实现高压缩率的同时，将准确率提升了高达28.1%。此外，我们证明了在证据压缩过程中参数化与非参数化知识的有效整合。