GeAR: Graph-enhanced Agent for Retrieval-augmented Generation

ACL ARR 2024 December Submission1252 Authors

Abstract: Retrieval-augmented generation systems rely on effective document retrieval capabilities. By design, conventional sparse or dense retrievers face challenges in multi-hop retrieval scenarios. In this paper, we present $\text{G\small{E}\normalsize{AR}}$, which advances RAG performance through two key innovations: (i) graph expansion, which enhances any conventional base retriever, such as BM25, and (ii) an agent framework that incorporates graph expansion. Our evaluation demonstrates $\text{G\small{E}\normalsize{AR}}$'s superior retrieval performance on three multi-hop question answering datasets. Additionally, our system achieves state-of-the-art results with improvements exceeding 10% on the challenging MuSiQue dataset, while requiring fewer tokens and iterations compared to other multi-step retrieval systems.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: retrieval-augmented generation, multihop QA

Languages Studied: English

Submission Number: 1252