mlsanityData to 14 Oct 2026

C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models

arXiv 2402.03181 ↗First posted 5 Feb 2024cs.AI cs.CL cs.IRcited by 27

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

Abstract (arXiv)

Despite the impressive capabilities of large language models (LLMs) across diverse applications, they still suffer from trustworthiness issues, such as hallucinations and misalignments. Retrieval-augmented language models (RAG) have been proposed to enhance the credibility of generations by grounding external knowledge, but the theoretical understandings of their generation risks remains unexplored. In this paper, we answer: 1) whether RAG can indeed lead to low generation risks, 2) how to provide provable guarantees on the generation risks of RAG and vanilla LLMs, and 3) what sufficient conditions enable RAG models to reduce generation risks. We propose C-RAG, the first framework to certify generation risks for RAG models. Specifically, we provide conformal risk analysis for RAG models and certify an upper confidence bound of generation risks, which we refer to as conformal generation risk. We also provide theoretical guarantees on conformal generation risks for general bounded risk functions under test distribution shifts. We prove that RAG achieves a lower conformal generation risk than that of a single LLM when the quality of the retrieval model and transformer is non-trivial. Our intensive empirical results demonstrate the soundness and tightness of our conformal generation risk guarantees across four widely-used NLP datasets on four state-of-the-art retrieval models.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 39 of its 65 references that are in the map. First posted on arXiv 5 Feb 2024.

Builds on

39 of 65 references.

References · 39

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  5. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  6. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
  7. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
  8. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 786
  9. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  10. 2022Transformers learn in-context by gradient descentcited by 732
  11. 2021Learning To Retrieve Prompts for In-Context Learningcited by 648
  12. 2022MTEB: Massive Text Embedding Benchmarkcited by 640
27 more
  1. 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Modelscited by 518
  2. 2023Trained Transformers Learn Linear Models In-Contextcited by 337
  3. 2022Conformal Risk Controlcited by 299
  4. 2021Distribution-Free, Risk-Controlling Prediction Setscited by 288
  5. 2024MM-LLMs: Recent Advances in MultiModal Large Language Modelscited by 278
  6. 2021Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Controlcited by 271
  7. 2017The E2E Dataset: New Challenges For End-to-End Generationcited by 253
  8. 2022Transformer Memory as a Differentiable Search Indexcited by 247
  9. 2022Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matterscited by 222
  10. 2017Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluationcited by 206
  11. 2023Compressing Context to Enhance Inference Efficiency of Large Language Modelscited by 189
  12. 2023Conformal Language Modelingcited by 170
  13. 2022Adaptive Conformal Predictions for Time Seriescited by 161
  14. 2022VLP: A Survey on Vision-Language Pre-trainingcited by 159
  15. 2016Variance-based regularization with convex objectivescited by 155
  16. 2020DART: Open-Domain Structured Data Record to Text Generationcited by 145
  17. 2022A Neural Corpus Indexer for Document Retrievalcited by 111
  18. 2023UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluationcited by 75
  19. 2023A Multi-Task Embedder For Retrieval Augmented LLMscited by 64
  20. 2023Learning to Retrieve In-Context Examples for Large Language Modelscited by 60
  21. 2019This Email Could Save Your Life: Introducing the Task of Email Subject Line Generationcited by 58
  22. 2023Augmented Large Language Models with Parametric Knowledge Guidingcited by 37
  23. 2023RAVEN: In-Context Learning with Retrieval-Augmented Encoder-Decoder Language Modelscited by 37
  24. 2023DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purificationcited by 36
  25. 2023Non-Exchangeable Conformal Risk Controlcited by 29
  26. 2023IncDSI: Incrementally Updatable Document Retrievalcited by 12
  27. 2022Certifying Out-of-Domain Generalization for Blackbox Functionscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 16; 2025: 5; 2026: 6.

27 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 354
  2. 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 127
  3. 2024Large language model validity via enhanced conformal prediction methodscited by 92
  4. 2024Adversarial Tuning: Defending Against Jailbreak Attacks for LLMscited by 26
  5. 2024Conformal Prediction: A Data Perspectivecited by 25
  6. 2025Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Surveycited by 20
  7. 2024FMint: Bridging Human Designed and Data Pretrained Models for Differential Equation Foundation Modelcited by 19
  8. 2024Hummer: Towards Limited Competitive Preference Datasetcited by 10
  9. 2024Certifying Counterfactual Bias in LLMscited by 10
  10. 2024Debate as Optimization: Adaptive Conformal Prediction and Diverse Retrieval for Event Extractioncited by 10
  11. 2024COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuitscited by 9
  12. 2024Certifiably Byzantine-Robust Federated Conformal Predictioncited by 8
15 more
  1. 2025Response Quality Assessment for Retrieval-Augmented Generation via Conditional Conformal Factualitycited by 8
  2. 2024Optimizing and Evaluating Enterprise Retrieval-Augmented Generation (RAG): A Content Design Perspectivecited by 7
  3. 2024FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guaranteescited by 7
  4. 2025Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attackscited by 7
  5. 2024CONFLARE: CONFormal LArge language model REtrievalcited by 6
  6. 2025Principled Context Engineering for RAG: Statistical Guarantees via Conformal Predictioncited by 6
  7. 2026RepoShapley: Shapley-Enhanced Context Filtering for Repository-Level Code Completioncited by 3
  8. 2024HRDE: Retrieval-Augmented Large Language Models for Chinese Health Rumor Detection and Explainabilitycited by 2
  9. 2024Do You Know What You Are Talking About? Characterizing Query-Knowledge Relevance For Reliable Retrieval Augmented Generationcited by 2
  10. 2025Windsock is Dancing: Adaptive Multimodal Retrieval-Augmented Generationcited by 1
  11. 2026Attribution Techniques for Mitigating Hallucinated Information in RAG Systems: A Surveycited by 0
  12. 2026Certified Domain Consistency for Multi-Domain Retrieval: Label-Free Per-Domain Contamination Control with Conformal Risk Guaranteescited by 0
  13. 2026Private Anytime Selective-Risk Certification for Federated Retrieval-Augmented Generation: Guarantees and Empirical Limitscited by 0
  14. 2026When Should Multi-Round RAG Stop? Structured Stopping Judgments and Retrieval Reduction in Search-R1cited by 0
  15. 2026Conformal Factuality Control for Multi-Hop Retrieval-Augmented Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Survey
  2. 2025RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models
  3. 2023Retrieval-Augmented Generation for Large Language Models: A Survey
  4. 2024Towards Understanding Systems Trade-offs in Retrieval-Augmented Generation Model Inference
  5. 2024Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework
  6. 2026RAG-Safety-Bench: Reliable Evaluation of Retrieval-Augmented LLM Safety
  7. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  8. 2024A Theory for Token-Level Harmonization in Retrieval-Augmented Generation