mlsanityData to 7 Oct 2026

Trustworthiness in Retrieval-Augmented Generation Systems: A Survey

arXiv 2409.10102 ↗First posted 16 Sep 2024cs.IR cs.AI cs.CLcited by 83

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

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) has quickly grown into a pivotal paradigm in the development of Large Language Models (LLMs). Although existing research mainly emphasizes accuracy and efficiency, the trustworthiness of RAG systems remains insufficiently explored. RAG can improve LLM reliability by grounding responses in external and up-to-date knowledge, reducing hallucinations. However, unreliable retrieval or improper knowledge utilization may still lead to undesirable outputs. To address these concerns, we propose a unified framework, Trust-RAG Compass, that assesses the trustworthiness of RAG systems across six key dimensions: factuality, robustness, fairness, transparency, accountability, and privacy. Within this framework, we provide a thorough review of the existing literature along each dimension. Furthermore, we introduce an evaluation benchmark, TRC Bench (underlineTrust-underlineRAG underlineCompass underlineBenchmark), regarding the six dimensions and conduct comprehensive evaluations for a variety of proprietary and open-source models. Our results shed light on the performance gaps between different types of LLMs across varying dimensions of trustworthiness. Finally, we identify key challenges and promising directions for future research based on our findings. Through this work, we aim to provide a structured foundation for subsequent investigations and practical guidance for developing trustworthy RAG systems in real-world scenarios.

Key facts. Cited by 83 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 120 of its 193 references that are in the map. First posted on arXiv 16 Sep 2024.

Builds on

120 of 193 references.

Closest ancestors · 9

Same direction, newest first

  1. 2024Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation1 Jul
  2. 2024FoRAG: Factuality-optimized Retrieval Augmented Generation for Web-enhanced Long-form Question Answering19 Jun
  3. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity21 Mar
  4. 2024BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting Evidence19 Feb
  5. 2024HGOT: Hierarchical Graph of Thoughts for Retrieval-Augmented In-Context Learning in Factuality Evaluation14 Feb
  6. 2023PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter23 Oct
  7. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct
  8. 2023Benchmarking Large Language Models in Retrieval-Augmented Generation4 Sep
  9. 2023Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise2 May

Other references · 111

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  7. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  8. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  9. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  10. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  11. 2023A Survey of Large Language Modelscited by 2,537
  12. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
38 more
  1. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  2. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  3. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,339
  4. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  5. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  6. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  7. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  8. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  9. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
  10. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  11. 2019Adversarial NLI: A New Benchmark for Natural Language Understandingcited by 798
  12. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  13. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  14. 2020Quantifying Attention Flow in Transformerscited by 759
  15. 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 703
  16. 2023Active Retrieval Augmented Generationcited by 506
  17. 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Modelscited by 505
  18. 2024AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Basescited by 402
  19. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 394
  20. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 351
  21. 2023Multi-step Jailbreaking Privacy Attacks on ChatGPTcited by 320
  22. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 296
  23. 2019A Multiscale Visualization of Attention in the Transformer Modelcited by 292
  24. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 286
  25. 2024TrustLLM: Trustworthiness in Large Language Modelscited by 280
  26. 2024PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Modelscited by 251
  27. 2023Certifying LLM Safety against Adversarial Promptingcited by 248
  28. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 233
  29. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 211
  30. 2022Are Large Pre-Trained Language Models Leaking Your Personal Information?cited by 195
  31. 2020How Context Affects Language Models' Factual Predictionscited by 181
  32. 2023GPT detectors are biased against non-native English writerscited by 175
  33. 2019Deep ReLU Networks Have Surprisingly Few Activation Patternscited by 160
  34. 2024The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)cited by 159
  35. 2023Take a Step Back: Evoking Reasoning via Abstraction in Large Language Modelscited by 157
  36. 2023Poisoning Retrieval Corpora by Injecting Adversarial Passagescited by 153
  37. 2024Certifiably Robust RAG against Retrieval Corruptioncited by 144
  38. 2020Algorithmic Fairnesscited by 143

50 most cited of 111 All 111 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 9; 2025: 51; 2026: 23.

83 papers.

Sort:

By area:

  1. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capabilitycited by 320
  2. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  3. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  4. 2024HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systemscited by 37
  5. 2025TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generationcited by 37
  6. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 34
  7. 2025Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlookcited by 32
  8. 2024Mask-based Membership Inference Attacks for Retrieval-Augmented Generationcited by 29
  9. 2025Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Surveycited by 29
  10. 2024Can Knowledge Editing Really Correct Hallucinations?cited by 28
  11. 2025RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defectscited by 27
  12. 2025The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMscited by 24
38 more
  1. 2025GraphRAG under Firecited by 23
  2. 2025RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Modelscited by 23
  3. 2026Sycophancy Hides Linearly in the Attention Headscited by 21
  4. 2024RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generationcited by 20
  5. 2025Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Surveycited by 20
  6. 2025Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foragingcited by 20
  7. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Surveycited by 18
  8. 2024Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Basescited by 17
  9. 2025Benchmarking Poisoning Attacks against Retrieval-Augmented Generationcited by 17
  10. 2025Hierarchical Document Refinement for Long-context Retrieval-augmented Generationcited by 16
  11. 2025EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corporacited by 14
  12. 2025Poisoned-MRAG: Knowledge Poisoning Attacks to Multimodal Retrieval Augmented Generationcited by 12
  13. 2025Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metricscited by 12
  14. 2025Understanding and Leveraging the Expert Specialization of Context Faithfulness in Mixture-of-Experts LLMscited by 12
  15. 2026OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAGcited by 11
  16. 2025Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Datacited by 10
  17. 2025Privacy-Aware RAG: Secure and Isolated Knowledge Retrievalcited by 10
  18. 2025C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generationcited by 9
  19. 2025The Singapore Consensus on Global AI Safety Research Prioritiescited by 9
  20. 2025Response Quality Assessment for Retrieval-Augmented Generation via Conditional Conformal Factualitycited by 8
  21. 2025QAgent: A modular Search Agent with Interactive Query Understandingcited by 8
  22. 2025Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrievalcited by 7
  23. 2025NeuroGenPoisoning: Neuron-Guided Attacks on Retrieval-Augmented Generation of LLM via Genetic Optimization of External Knowledgecited by 7
  24. 2026SoK: Privacy Risks and Mitigations in Retrieval-Augmented Generation Systemscited by 7
  25. 2026Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimizationcited by 7
  26. 2024AssistRAG: Boosting the Potential of Large Language Models with an Intelligent Information Assistantcited by 5
  27. 2025Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domainscited by 5
  28. 2025Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generationcited by 5
  29. 2025Token-Level Precise Attack on RAG: Searching for the Best Alternatives to Mislead Generationcited by 5
  30. 2025Parametric Retrieval-Augmented Generation using Latent Routing of LoRA Adapterscited by 5
  31. 2026Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generationcited by 5
  32. 2025Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citationcited by 4
  33. 2024What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context for Multi-Hop QAcited by 3
  34. 2025Bridging External and Parametric Knowledge: Mitigating Hallucination of LLMs with Shared-Private Semantic Synergy in Dual-Stream Knowledgecited by 3
  35. 2025ConfRAG: Confidence-Guided Retrieval-Augmenting Generationcited by 3
  36. 2025Multi-Agent Retrieval-Augmented Framework for Evidence-Based Counterspeech Against Health Misinformationcited by 3
  37. 2026IMRNNs: An Efficient Method for Interpretable Dense Retrieval via Embedding Modulationcited by 3
  38. 2025Investigating Retrieval-Augmented Generation in Quranic Studies: A Study of 13 Open-Source Large Language Modelscited by 2

50 most cited of 83 All 83 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025After Retrieval, Before Generation: Enhancing the Trustworthiness of Large Language Models in Retrieval-Augmented Generation
  2. 2024C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models
  3. 2025The Other Side of the Coin: Exploring Fairness in Retrieval-Augmented Generation
  4. 2026RAG-Safety-Bench: Reliable Evaluation of Retrieval-Augmented LLM Safety
  5. 2024Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse
  6. 2023Retrieval-Augmented Generation for Large Language Models: A Survey
  7. 2025Evaluating the Retrieval Robustness of Large Language Models
  8. 2024Retrieval-Augmented Generation with Estimation of Source Reliability