mlsanityData to 7 Oct 2026

Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation

arXiv 2406.13692 ↗First posted 19 Jun 2024cs.CLcited by 6

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

Abstract (arXiv)

Retrieval-augmented language models (RALMs) have shown strong performance and wide applicability in knowledge-intensive tasks. However, there are significant trustworthiness concerns as RALMs are prone to generating unfaithful outputs, including baseless information or contradictions with the retrieved context. This paper proposes SynCheck, a lightweight monitor that leverages fine-grained decoding dynamics including sequence likelihood, uncertainty quantification, context influence, and semantic alignment to synchronously detect unfaithful sentences. By integrating efficiently measurable and complementary signals, SynCheck enables accurate and immediate feedback and intervention, achieving 0.85 AUROC in detecting faithfulness errors across six long-form retrieval-augmented generation tasks, improving prior best method by 4%. Leveraging SynCheck, we further introduce FOD, a faithfulness-oriented decoding algorithm guided by beam search for long-form retrieval-augmented generation. Empirical results demonstrate that FOD outperforms traditional strategies such as abstention, reranking, or contrastive decoding significantly in terms of faithfulness, achieving over 10% improvement across six datasets.

Key facts. Cited by 6 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 36 of its 47 references that are in the map. First posted on arXiv 19 Jun 2024.

Builds on

36 of 47 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents16 Apr
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 34

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  6. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  7. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  8. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  9. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  10. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,259
  11. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,259
  12. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
22 more
  1. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  2. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  3. 2023Large Language Modelscited by 774
  4. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  5. 2023The Internal State of an LLM Knows When It's Lyingcited by 644
  6. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
  7. 2021Entity-Based Knowledge Conflicts in Question Answeringcited by 349
  8. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 343
  9. 2023Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflictscited by 333
  10. 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 319
  11. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 286
  12. 2023AlignScore: Evaluating Factual Consistency with a Unified Alignment Functioncited by 284
  13. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Modelscited by 272
  14. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 253
  15. 2020Selective Question Answering under Domain Shiftcited by 228
  16. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 193
  17. 2024Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaborationcited by 176
  18. 2024Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimensioncited by 45
  19. 2024On Large Language Models' Hallucination with Regard to Known Factscited by 43
  20. 2023Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimationcited by 38
  21. 2024How well do LLMs cite relevant medical references? An evaluation framework and analysescited by 20
  22. 2024Fine-Grained Self-Endorsement Improves Factuality and Reasoningcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 2.

6 papers.

  1. 2025Where Did It All Go Wrong? A Hierarchical Look into Multi-Agent Error Attributioncited by 25
  2. 2025Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalizationcited by 9
  3. 2025Response Quality Assessment for Retrieval-Augmented Generation via Conditional Conformal Factualitycited by 8
  4. 2026Detecting Hallucinations in Retrieval-Augmented Generation via Semantic-level Internal Reasoning Graphcited by 2
  5. 2025RAG-PRISM: A Personalized, Rapid, and Immersive Skill Mastery Framework with Adaptive Retrieval-Augmented Tutoringcited by 1
  6. 2026Document-Authored Control-Signal Impersonation: A Low-Cost Indirect Prompt Attack on RAG Safety Boundariescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025SSFO: Self-Supervised Faithfulness Optimization for Retrieval-Augmented Generation
  2. 2025Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization
  3. 2025Retrieval-augmented Decoding for Improving Truthfulness in Open-ended Generation
  4. 2026Faithfulness Is Not Free: Auditing Offline KV-Cache Quantization in Retrieval-Augmented Generation
  5. 2024FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"
  6. 2026Reason and Verify: A Framework for Faithful Retrieval-Augmented Generation
  7. 2026When Context Misleads: Intent-Guided Decoding for Robust Retrieval-Augmented Generation
  8. 2025After Retrieval, Before Generation: Enhancing the Trustworthiness of Large Language Models in Retrieval-Augmented Generation