QuIM-RAG：利用反向问题匹配推进检索增强生成以提升问答性能
QuIM-RAG: Advancing Retrieval-Augmented Generation with Inverted Question Matching for Enhanced QA Performance
AI总结：
本文提出QuIM-RAG，通过从文档块生成潜在问题并与用户查询进行倒排索引匹配来改进检索，在500多页自定义语料库上以BERT-Score和RAGAS验证其优于传统RAG。
摘要：
本工作提出了一种用于构建检索增强生成（RAG）系统的新型架构，以改进基于目标语料库的问答（QA）任务。大型语言模型（LLM）已经彻底改变了类人文本的分析与生成。这些模型依赖预训练数据，除非与实时数据工具集成，否则缺乏实时更新能力。RAG通过整合在线资源和数据库来增强LLM，以生成符合上下文的回答。然而，传统RAG在处理海量数据时仍面临信息稀释和幻觉等挑战。我们的方法通过将语料库转换为特定领域数据集来应对这些挑战，并构建RAG架构以根据目标文档生成回答。我们引入了QuIM-RAG（Question-to-question Inverted Index Matching，问题到问题倒排索引匹配），这是系统检索机制中的一种新方法。该策略从文档块生成潜在问题，并将这些问题与用户查询匹配，以识别最相关的文本块，从而生成准确答案。我们在Meta Inc.开源、可在Hugging Face上获取的Meta-LLaMA3-8B-instruct模型之上实现了RAG系统。我们构建了一个包含500多页内容的自定义语料库，这些内容来自一个每天被访问数千次的高流量网站，用于回答复杂问题；同时还准备了人工编写的真值QA用于评估。我们使用BERT-Score和RAGAS这两种评估LLM应用的先进指标，将所提方法与传统RAG模型进行了比较。评估表明，我们的方法在两项指标上均优于传统RAG架构。
英文摘要：
This work presents a novel architecture for building Retrieval-Augmented Generation (RAG) systems to improve Question Answering (QA) tasks from a target corpus. Large Language Models (LLMs) have revolutionized the analyzing and generation of human-like text. These models rely on pre-trained data and lack real-time updates unless integrated with live data tools. RAG enhances LLMs by integrating online resources and databases to generate contextually appropriate responses. However, traditional RAG still encounters challenges like information dilution and hallucinations when handling vast amounts of data. Our approach addresses these challenges by converting corpora into a domain-specific dataset and RAG architecture is constructed to generate responses from the target document. We introduce QuIM-RAG (Question-to-question Inverted Index Matching), a novel approach for the retrieval mechanism in our system. This strategy generates potential questions from document chunks and matches these with user queries to identify the most relevant text chunks for generating accurate answers. We have implemented our RAG system on top of the open-source Meta-LLaMA3-8B-instruct model by Meta Inc. that is available on Hugging Face. We constructed a custom corpus of 500+ pages from a high-traffic website accessed thousands of times daily for answering complex questions, along with manually prepared ground truth QA for evaluation. We compared our approach with traditional RAG models using BERT-Score and RAGAS, state-of-the-art metrics for evaluating LLM applications. Our evaluation demonstrates that our approach outperforms traditional RAG architectures on both metrics.
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。
