mlsanityData to 7 Oct 2026

CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG

arXiv 2406.11497 ↗First posted 17 Jun 2024cs.CLcited by 22

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) can alleviate hallucinations of Large Language Models (LLMs) by referencing external documents. However, the misinformation in external documents may mislead LLMs' generation. To address this issue, we explore the task of "credibility-aware RAG", in which LLMs automatically adjust the influence of retrieved documents based on their credibility scores to counteract misinformation. To this end, we introduce a plug-and-play method named Credibility-aware Attention Modification (CrAM). CrAM identifies influential attention heads in LLMs and adjusts their attention weights based on the credibility of the documents, thereby reducing the impact of low-credibility documents. Experiments on Natual Questions and TriviaQA using Llama2-13B, Llama3-8B, and Qwen1.5-7B show that CrAM improves the RAG performance of LLMs against misinformation pollution by over 20%, even surpassing supervised fine-tuning methods.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 30 of its 50 references that are in the map. First posted on arXiv 17 Jun 2024.

Builds on

30 of 50 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation10 Apr
  2. 2024Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models22 Feb
  3. 2023Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise2 May

Other references · 27

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  6. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  7. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  8. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  9. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  10. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  11. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  12. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
15 more
  1. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  2. 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 994
  3. 2019Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Prunedcited by 844
  4. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  5. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
  6. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  7. 2023Can LLM-Generated Misinformation Be Detected?cited by 173
  8. 2024Certifiably Robust RAG against Retrieval Corruptioncited by 144
  9. 2023Towards Reliable Misinformation Mitigation: Generalization, Uncertainty, and GPT-4cited by 45
  10. 2021Attacking Open-domain Question Answering by Injecting Misinformationcited by 41
  11. 2024AMMeBa: A Large-Scale Survey and Dataset of Media-Based Misinformation In-The-Wildcited by 26
  12. 2023Interpretable Multimodal Misinformation Detection with Logic Reasoningcited by 16
  13. 2019Do Sentence Interactions Matter? Leveraging Sentence Level Representations for Fake News Classificationcited by 15
  14. 2022Defending Against Disinformation Attacks in Open-Domain Question Answeringcited by 12
  15. 2019The Future of Misinformation Detection: New Perspectives and Trendscited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 9; 2026: 10.

22 papers.

Sort:

By area:

  1. 2025Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Surveycited by 29
  2. 2024Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMscited by 23
  3. 2024Retrieval-Augmented Generation with Estimation of Source Reliabilitycited by 19
  4. 2024FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAGcited by 18
  5. 2025ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Searchcited by 17
  6. 2025Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignmentcited by 15
  7. 2025ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentationcited by 12
  8. 2026OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAGcited by 11
  9. 2025Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safetycited by 10
  10. 2025Source Coverage and Citation Bias in LLM-based vs. Traditional Search Enginescited by 4
  11. 2025GETReason: Enhancing Image Context Extraction through Hierarchical Multi-Agent Reasoningcited by 3
  12. 2025Memory Helps, but Confabulation Misleads: Understanding Streaming Events in Videos with MLLMscited by 2
10 more
  1. 2026Tackling the Inherent Difficulty of Noise Filtering in RAGcited by 2
  2. 2026RAGExplorer: A Visual Analytics System for the Comparative Diagnosis of RAG Systemscited by 2
  3. 2026Misinformation Propagation in Benign Multi-Agent Systemscited by 2
  4. 2025CrEst: Credibility Estimation for Contexts in LLMs via Weak Supervisioncited by 0
  5. 2026AuthorityBench: Benchmarking LLM Authority Perception for Reliable Retrieval-Augmented Generationcited by 0
  6. 2026RAGSieve: Self-Referenced Local Contrast for Knowledge-Poison Detection in Retrieval-Augmented Generationcited by 0
  7. 2026RAGSentinel: Certifiable Geometric Consensus for Robust Retrieval-Augmented Generationcited by 0
  8. 2026CiteShade: Citation Laundering in Multi-Source Retrieval-Augmented Generation and Its Counterfactual Defensecited by 0
  9. 2026BaRe-Mem: Bayesian Reliability Memory for Robust and Adaptive Agent Consultationcited by 0
  10. 2026Multi-Channel Mitigation of Source-Trust Shortcuts in Fact-Checking RL Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals
  2. 2024Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases
  3. 2024Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output
  4. 2025Finetune-RAG: Fine-Tuning Language Models to Resist Hallucination in Retrieval-Augmented Generation
  5. 2024CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control
  6. 2025Contradiction Detection in RAG Systems: Evaluating LLMs as Context Validators for Improved Information Consistency
  7. 2026Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation
  8. 2025Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMs