arXiv 2402.174972024-11-21cs.CLcs.IR

REAR：一种面向开放域问答的相关性感知检索增强框架

REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering

Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；National University of Singapore（新加坡国立大学）；Baidu Inc.（百度公司）；School of Information, Renmin University of China（中国人民大学信息学院）

Yuhao Wang, Ruiyang Ren, Junyi Li, Wayne Xin Zhao, Jing Liu, Ji-Rong Wen

备注：: Accepted to EMNLP 2024 Main Conference. Published on ACL Anthology: https://aclanthology.org/2024.emnlp-main.321.pdf

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出REAR框架，通过相关性评估模块与双粒度相关性融合及抗噪训练，增强大语言模型对检索文档相关性的感知能力，从而在开放域问答中更可靠地利用外部知识并显著超越现有RAG方法。

摘要：

考虑到大语言模型（LLMs）内部参数化知识有限，检索增强生成（RAG）已被广泛用于扩展大语言模型的知识范围。尽管RAG研究已有大量努力，但在现有方法中，大语言模型无法精确评估检索文档的相关性，因此可能导致对外部知识（例如检索到的文档）的误导性甚至错误利用。为解决这一问题，本文提出REAR，一种面向开放域问答（QA）的相关性感知检索增强方法。其核心动机在于增强大语言模型对外部知识可靠性的自我感知，从而在RAG系统中自适应地利用外部知识。具体而言，我们为基于LLM的RAG系统开发了一种新颖架构，引入一个专门设计的评估模块，用于精确评估检索文档的相关性。此外，我们提出一种基于双粒度相关性融合和抗噪训练的改进训练方法。通过结合架构与训练两方面的改进，所提出的REAR能够通过有效感知检索文档的相关性来更好地利用外部知识。在四个开放域问答任务上的实验表明，REAR显著优于此前多种有竞争力的RAG方法。我们的代码可在https://github.com/RUCAIBox/REAR获取。

英文摘要：

Considering the limited internal parametric knowledge, retrieval-augmented generation (RAG) has been widely used to extend the knowledge scope of large language models (LLMs). Despite the extensive efforts on RAG research, in existing methods, LLMs cannot precisely assess the relevance of retrieved documents, thus likely leading to misleading or even incorrect utilization of external knowledge (eg., retrieved documents). To address this issue, in this paper, we propose REAR, a RElevance-Aware Retrieval-augmented approach for open-domain question answering (QA). As the key motivation, we aim to enhance the self-awareness regarding the reliability of external knowledge for LLMs, so as to adaptively utilize external knowledge in RAG systems. Specially, we develop a novel architecture for LLM-based RAG systems, by incorporating a specially designed assessment module that precisely assesses the relevance of retrieved documents. Furthermore, we propose an improved training method based on bi-granularity relevance fusion and noise-resistant training. By combining the improvements in both architecture and training, our proposed REAR can better utilize external knowledge by effectively perceiving the relevance of retrieved documents. Experiments on four open-domain QA tasks show that REAR significantly outperforms previous a number of competitive RAG approaches. Our codes can be accessed at https://github.com/RUCAIBox/REAR.

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。