BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting Evidence

Jiajie Jin, Yutao Zhu, Yujia Zhou, Zhicheng Dou


Abstract
Retrieval-augmented large language models (LLMs) have demonstrated efficacy in knowledge-intensive tasks such as open-domain QA, addressing inherent challenges in knowledge update and factual inadequacy.However, inconsistencies between retrieval knowledge and the necessary knowledge for LLMs, leading to a decline in LLM’s answer quality. This paper introduces BIDER, an approach that refines retrieval documents into Key Supporting Evidence (KSE) through knowledge synthesis, supervised fine-tuning (SFT), and preference alignment. We train BIDER by learning from crafting KSE, while maximizing its output to align with LLM’s information acquisition preferences through reinforcement learning. Evaluations across five datasets show BIDER boosts LLMs’ answer quality by 7% while reducing input content length in retrieval documents by 80%, outperforming existing methods. The proposed KSE simulation effectively equips LLMs with essential information for accurate question answering.
Anthology ID:
2024.findings-acl.42
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
750–761
Language:
URL:
https://aclanthology.org/2024.findings-acl.42
DOI:
10.18653/v1/2024.findings-acl.42
Bibkey:
Cite (ACL):
Jiajie Jin, Yutao Zhu, Yujia Zhou, and Zhicheng Dou. 2024. BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting Evidence. In Findings of the Association for Computational Linguistics: ACL 2024, pages 750–761, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting Evidence (Jin et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/autopr/2024.findings-acl.42.pdf