通过突出语用相关句，让检索增强生成更精准
Say Less, Mean More: Leveraging Pragmatics in Retrieval-Augmented Generation
- 仅标记相关句子，不删改原文上下文
- 在三个问答任务上最高提升19.7%准确率
- 适配多种大模型，无需额外训练
我们提出一种简单且无监督的方法，将语用原则注入检索增强生成（RAG）框架，如稠密段落检索，以提升检索内容的实用性。该方法首先识别出与问题最相关的句子：既要涵盖问题涉及的所有主题，又不超出范围；然后在不截断或修改上下文的前提下，将这些句子高亮后提供给大模型。实验表明，这一方法在三个问答任务（ARC-Challenge、PubHealth、PopQA）上均带来稳定提升，使用五种不同大模型时，相较传统RAG系统，在PubHealth任务上相对准确率最高提升19.7%，在ARC-Challenge任务上提升10%。
原文摘要 · Abstract (English)
We propose a simple, unsupervised method that injects pragmatic principles in retrieval-augmented generation (RAG) frameworks such as Dense Passage Retrieval to enhance the utility of retrieved contexts. Our approach first identifies which sentences in a pool of documents retrieved by RAG are most relevant to the question at hand, cover all the topics addressed in the input question and no more, and then highlights these sentences within their context, before they are provided to the LLM, without truncating or altering the context in any other way. We show that this simple idea brings consistent improvements in experiments on three question answering tasks (ARC-Challenge, PubHealth and PopQA) using five different LLMs. It notably enhances relative accuracy by up to 19.7% on PubHealth and 10% on ARC-Challenge compared to a conventional RAG system.
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。