M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions

Zheng Wang, Shu Teo, Jieer Ouyang, Yongjun Xu, Wei Shi

Abstract
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by retrieving relevant memories from an external database. However, existing RAG methods typically organize all memories in a whole database, potentially limiting focus on crucial memories and introducing noise. In this paper, we introduce a multiple partition paradigm for RAG (called M-RAG), where each database partition serves as a basic unit for RAG execution. Based on this paradigm, we propose a novel framework that leverages LLMs with Multi-Agent Reinforcement Learning to optimize different language generation tasks explicitly. Through comprehensive experiments conducted on seven datasets, spanning three language generation tasks and involving three distinct language model architectures, we confirm that M-RAG consistently outperforms various baseline methods, achieving improvements of 11%, 8%, and 12% for text summarization, machine translation, and dialogue generation, respectively.
Anthology ID:
2024.acl-long.108
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1966–1978
Language:
URL:
https://aclanthology.org/2024.acl-long.108
DOI:
10.18653/v1/2024.acl-long.108
Bibkey:
Cite (ACL):
Zheng Wang, Shu Teo, Jieer Ouyang, Yongjun Xu, and Wei Shi. 2024. M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1966–1978, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions (Wang et al., ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/autopr/2024.acl-long.108.pdf
PDF Search Fix metadata