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

TL;DR

BIDER enhances retrieval-augmented LLMs by synthesizing key supporting evidence, improving answer quality and reducing retrieval content size through knowledge refinement and reinforcement learning.

Contribution

The paper introduces BIDER, a novel method for refining retrieval documents into key supporting evidence to improve LLM performance and efficiency.

Findings

Boosts LLM answer quality by 7%

Reduces retrieval document size by 80%

Outperforms existing methods across datasets

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.