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

2024/02/19 by Jiajie Jin, Yutao Zhu, Jin, Jiajie +5 · 3 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Semantic Web and Ontologies

paper · pdf · doi:10.48550/arxiv.2402.12174

openalex publication_date 2024/02/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Cited by

• CodeRAG: Finding Relevant and Necessary Knowledge for Retrieval-Augmented Repository-Level Code Completion
• CORE-RAG: Lossless Compression for Retrieval-Augmented LLMs via Reinforcement Learning
• From Matching to Generation: A Survey on Generative Information Retrieval

Related

• Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs
• Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation
• Improving Context Fidelity via Native Retrieval-Augmented Reasoning
• R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning
• Beyond Self-Knowledge: Propagating Uncertainty Across Reasoning and Retrieval in LLMs