An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generation

Kun Zhu, Xiaocheng Feng, Xiyuan Du, Yuxuan Gu, Weijiang Yu, Haotian Wang, Qianglong Chen, Zheng Chu, Jingchang Chen, Bing Qin


Abstract
Retrieval-augmented generation integrates the capabilities of large language models with relevant information retrieved from an extensive corpus, yet encounters challenges when confronted with real-world noisy data. One recent solution is to train a filter module to find relevant content but only achieve suboptimal noise compression. In this paper, we propose to introduce the information bottleneck theory into retrieval-augmented generation. Our approach involves the filtration of noise by simultaneously maximizing the mutual information between compression and ground output, while minimizing the mutual information between compression and retrieved passage. In addition, we derive the formula of information bottleneck to facilitate its application in novel comprehensive evaluations, the selection of supervised fine-tuning data, and the construction of reinforcement learning rewards. Experimental results demonstrate that our approach achieves significant improvements across various question answering datasets, not only in terms of the correctness of answer generation but also in the conciseness with 2.5% compression rate.
Anthology ID:
2024.acl-long.59
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:
1044–1069
Language:
URL:
https://aclanthology.org/2024.acl-long.59
DOI:
10.18653/v1/2024.acl-long.59
Bibkey:
Cite (ACL):
Kun Zhu, Xiaocheng Feng, Xiyuan Du, Yuxuan Gu, Weijiang Yu, Haotian Wang, Qianglong Chen, Zheng Chu, Jingchang Chen, and Bing Qin. 2024. An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1044–1069, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generation (Zhu et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.59.pdf