Lune

ACL Findings2024

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 opendomain 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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

16 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems cites Training language models to follow instructions with human feedback
  • HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems cites Search-o1: Agentic Search-Enhanced Large Reasoning Models
  • Improving Language Models by Retrieving from Trillions of Tokens cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
  • WebThinker: Empowering Large Reasoning Models with Deep Research Capability cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
  • WebThinker: Empowering Large Reasoning Models with Deep Research Capability cites Search-o1: Agentic Search-Enhanced Large Reasoning Models
  • One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models cites Improving Language Models by Retrieving from Trillions of Tokens
  • One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
  • Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks cites BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
  • Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation cites Training language models to follow instructions with human feedback
  • Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
  • Search-o1: Agentic Search-Enhanced Large Reasoning Models cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
  • Search-o1: Agentic Search-Enhanced Large Reasoning Models cites Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers16

  1. WebThinker: Empowering Large Reasoning Models with Deep Research CapabilityXiaoxi Li, Jiajie Jin, Guanting Dong, Hongjin Qian et al.NeurIPS 2025 · 354 citations
  2. Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented GenerationGuanting Dong, Yutao Zhu, Chenghao Zhang, Zechen Wang et al.WWW 2025 · 44 citations
  3. HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG SystemsJiejun Tan, Zhicheng Dou, Wen Wang, Mang Wang et al.WWW 2025 · 42 citations
  4. Search-o1: Agentic Search-Enhanced Large Reasoning ModelsXiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang et al.EMNLP 2025 · 12 citations
  5. One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language ModelsYutao Zhu, Zhaoheng Huang, Zhicheng Dou, Ji-Rong WenAAAI 2025 · 9 citations

Builds on18

  1. Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
  2. Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
  3. Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan et al.NeurIPS 2023 · 5,828 citations
  4. Improving Language Models by Retrieving from Trillions of TokensSebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai et al.ICML 2022 · 1,629 citations
  5. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations

Related papers

  1. RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within GenerationXiaoxi Li, Jiajie Jin, Yujia Zhou, Yongkang Wu et al.ACL 2025
  2. Retrieval Augmented Language Model Pre-TrainingKelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat et al.ICML 2020 · 2,937 citations
  3. SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMsJaehyung Kim, Jaehyun Nam, Sangwoo Mo, Jongjin Park et al.ICLR 2024 · 89 citations
  4. REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question AnsweringYuhao Wang, Ruiyang Ren, Junyi Li, Xin Zhao et al.EMNLP 2024 · 12 citations
  5. QPaug: Question and Passage Augmentation for Open-Domain Question Answering of LLMsMinsang Kim, Cheoneum Park, Seung BaekEMNLP Findings 2024 · 5 citations
Dusk over the sea between two cliffs drawn in fine vertical lines