GeAR: Graph-enhanced Agent for Retrieval-augmented Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shen, Zhili, Diao, Chenxin, Vougiouklis, Pavlos, Merita, Pascual, Piramanayagam, Shriram, Chen, Enting, Graux, Damien, Melo, Andre, Lai, Ruofei, Jiang, Zeren, Li, Zhongyang, QI, YE, Ren, Yang, Tu, Dandan, Pan, Jeff Z.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912443560624128
author Shen, Zhili
Diao, Chenxin
Vougiouklis, Pavlos
Merita, Pascual
Piramanayagam, Shriram
Chen, Enting
Graux, Damien
Melo, Andre
Lai, Ruofei
Jiang, Zeren
Li, Zhongyang
QI, YE
Ren, Yang
Tu, Dandan
Pan, Jeff Z.
author_facet Shen, Zhili
Diao, Chenxin
Vougiouklis, Pavlos
Merita, Pascual
Piramanayagam, Shriram
Chen, Enting
Graux, Damien
Melo, Andre
Lai, Ruofei
Jiang, Zeren
Li, Zhongyang
QI, YE
Ren, Yang
Tu, Dandan
Pan, Jeff Z.
contents Retrieval-augmented Generation (RAG) relies on effective retrieval capabilities, yet traditional sparse and dense retrievers inherently struggle with multi-hop retrieval scenarios. In this paper, we introduce GeAR, a system that advances RAG performance through two key innovations: (i) an efficient graph expansion mechanism that augments any conventional base retriever, such as BM25, and (ii) an agent framework that incorporates the resulting graph-based retrieval into a multi-step retrieval framework. Our evaluation demonstrates GeAR's superior retrieval capabilities across three multi-hop question answering datasets. Notably, our system achieves state-of-the-art results with improvements exceeding 10% on the challenging MuSiQue dataset, while consuming fewer tokens and requiring fewer iterations than existing multi-step retrieval systems. The project page is available at https://gear-rag.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18431
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GeAR: Graph-enhanced Agent for Retrieval-augmented Generation
Shen, Zhili
Diao, Chenxin
Vougiouklis, Pavlos
Merita, Pascual
Piramanayagam, Shriram
Chen, Enting
Graux, Damien
Melo, Andre
Lai, Ruofei
Jiang, Zeren
Li, Zhongyang
QI, YE
Ren, Yang
Tu, Dandan
Pan, Jeff Z.
Computation and Language
Artificial Intelligence
Information Retrieval
Retrieval-augmented Generation (RAG) relies on effective retrieval capabilities, yet traditional sparse and dense retrievers inherently struggle with multi-hop retrieval scenarios. In this paper, we introduce GeAR, a system that advances RAG performance through two key innovations: (i) an efficient graph expansion mechanism that augments any conventional base retriever, such as BM25, and (ii) an agent framework that incorporates the resulting graph-based retrieval into a multi-step retrieval framework. Our evaluation demonstrates GeAR's superior retrieval capabilities across three multi-hop question answering datasets. Notably, our system achieves state-of-the-art results with improvements exceeding 10% on the challenging MuSiQue dataset, while consuming fewer tokens and requiring fewer iterations than existing multi-step retrieval systems. The project page is available at https://gear-rag.github.io.
title GeAR: Graph-enhanced Agent for Retrieval-augmented Generation
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2412.18431