mlsanityData to 7 Oct 2026

Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation

arXiv 2404.06809 ↗First posted 10 Apr 2024cs.CLcited by 21

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

Abstract (arXiv)

The rapid development of large language models has led to the widespread adoption of Retrieval-Augmented Generation (RAG), which integrates external knowledge to alleviate knowledge bottlenecks and mitigate hallucinations. However, the existing RAG paradigm inevitably suffers from the impact of flawed information introduced during the retrieval phrase, thereby diminishing the reliability and correctness of the generated outcomes. In this paper, we propose Credibility-aware Generation (CAG), a universally applicable framework designed to mitigate the impact of flawed information in RAG. At its core, CAG aims to equip models with the ability to discern and process information based on its credibility. To this end, we propose an innovative data transformation framework that generates data based on credibility, thereby effectively endowing models with the capability of CAG. Furthermore, to accurately evaluate the models' capabilities of CAG, we construct a comprehensive benchmark covering three critical real-world scenarios. Experimental results demonstrate that our model can effectively understand and utilize credibility for generation, significantly outperform other models with retrieval augmentation, and exhibit resilience against the disruption caused by noisy documents, thereby maintaining robust performance. Moreover, our model supports customized credibility, offering a wide range of potential applications.

Key facts. Cited by 21 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 34 of its 48 references that are in the map. First posted on arXiv 10 Apr 2024.

Builds on

34 of 48 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 33

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  4. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  6. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,271
  7. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  8. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  9. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  10. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 893
  11. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  12. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
21 more
  1. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
  2. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  3. 2019ELI5: Long Form Question Answeringcited by 567
  4. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 457
  5. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
  6. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 351
  7. 2023Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflictscited by 333
  8. 2016NewsQA: A Machine Comprehension Datasetcited by 330
  9. 2022RealTime QA: What's the Answer Right Now?cited by 239
  10. 2022OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalizationcited by 235
  11. 2022ASQA: Factoid Questions Meet Long-Form Answerscited by 231
  12. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 204
  13. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  14. 2023Can LLM-Generated Misinformation Be Detected?cited by 173
  15. 2022Large Language Models with Controllable Working Memorycited by 169
  16. 2021SPLADE v2: Sparse Lexical and Expansion Model for Information Retrievalcited by 126
  17. 2024What Evidence Do Language Models Find Convincing?cited by 74
  18. 2023Knowledge-Augmented Large Language Models for Personalized Contextual Query Suggestioncited by 43
  19. 2023Mitigating Temporal Misalignment by Discarding Outdated Factscited by 21
  20. 2022Improving Temporal Generalization of Pre-trained Language Models with Lexical Semantic Changecited by 18
  21. 2020Two Stage Transformer Model for COVID-19 Fake News Detection and Fact Checkingcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 8; 2026: 6.

21 papers.

Sort:

By area:

  1. 2024Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Modelscited by 57
  2. 2025DeepRAG: Thinking to Retrieve Step by Step for Large Language Modelscited by 37
  3. 2024To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contextscited by 25
  4. 2024CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAGcited by 22
  5. 2025A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applicationscited by 21
  6. 2024Retrieval-Augmented Generation with Estimation of Source Reliabilitycited by 19
  7. 2024Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineeringcited by 16
  8. 2024Evaluating the External and Parametric Knowledge Fusion of Large Language Modelscited by 9
  9. 2026Whose Facts Win? LLM Source Preferences under Knowledge Conflictscited by 8
  10. 2025Influence Guided Context Selection for Effective Retrieval-Augmented Generationcited by 6
  11. 2025FamilyTool: A Multi-hop Personalized Tool Use Benchmarkcited by 5
  12. 2025Impact-driven Context Filtering For Cross-file Code Completioncited by 5
9 more
  1. 2025Evaluating the Retrieval Robustness of Large Language Modelscited by 2
  2. 2026RAGExplorer: A Visual Analytics System for the Comparative Diagnosis of RAG Systemscited by 2
  3. 2026Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directionscited by 2
  4. 2025Context Selection and Rewriting for Video-based Educational Question Generationcited by 1
  5. 2024Maintaining Informative Coherence: Migrating Hallucinations in Large Language Models via Absorbing Markov Chainscited by 0
  6. 2025CrEst: Credibility Estimation for Contexts in LLMs via Weak Supervisioncited by 0
  7. 2026AuthorityBench: Benchmarking LLM Authority Perception for Reliable Retrieval-Augmented Generationcited by 0
  8. 2026Predictive Prefetching for Retrieval-Augmented Generationcited by 0
  9. 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. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Survey
  2. 2025After Retrieval, Before Generation: Enhancing the Trustworthiness of Large Language Models in Retrieval-Augmented Generation
  3. 2026Evaluating RAG Reliability under Clean, Misleading, and Mixed Retrieval
  4. 2024C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models
  5. 2025Contradiction Detection in RAG Systems: Evaluating LLMs as Context Validators for Improved Information Consistency
  6. 2026RAG-Safety-Bench: Reliable Evaluation of Retrieval-Augmented LLM Safety
  7. 2024CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control
  8. 2026In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning