mlsanityData to 14 Oct 2026

When Context Misleads: Intent-Guided Decoding for Robust Retrieval-Augmented Generation

arXiv 2608.16515 ↗First posted 17 Aug 2026cs.CL cs.AIcited by 0

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

Abstract (arXiv)

Retrieval-augmented generation (RAG) improves large language models by grounding generation in external evidence, but it also introduces a source trust problem: retrieved context may be useful, irrelevant, or even misleading. Existing RAG systems often apply a fixed trust policy toward retrieved evidence, which can either over-trust incorrect context or underuse context when the user explicitly asks for context-following behavior. Therefore, we propose Intent-Guided Decoding (IGD), a framework that arbitrates between retrieved context and parametric memory according to user intent. IGD uses answer-level filtering and token-level correction to steer the final decoding trajectory between retrieved context and parametric memory. We evaluate IGD on three faithful QA benchmarks and three factual-conflict benchmarks across five LLMs, IGD substantially improves factual recovery, achieving gains of up to 65.4 percentage points on factual-conflict benchmarks over Direct RAG, while preserving or improving strict context-following behavior, this findings highlight the importance of balancing factuality and faithfulness in RAG.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 42 of its 46 references that are in the map. First posted on arXiv 17 Aug 2026.

Builds on

42 of 46 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025Rethinking All Evidence: Enhancing Trustworthy Retrieval-Augmented Generation via Conflict-Driven Summarization2 Jul
  2. 2025FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation10 Jun
  3. 2025Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generation27 May
  4. 2025Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMs23 May
  5. 2025Retrieval-Augmented Generation with Conflicting Evidence17 Apr
  6. 2024To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts18 Oct
  7. 2024FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"30 Sep
  8. 2024ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence16 Apr
  9. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 33

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2024Qwen2.5 Technical Reportcited by 4,942
  5. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  6. 2023Mistral 7Bcited by 3,164
  7. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  8. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  9. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  10. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  11. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  12. 2024Phi-4 Technical Reportcited by 711
21 more
  1. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  2. 2022Contrastive Decoding: Open-ended Text Generation as Optimizationcited by 609
  3. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 573
  4. 2023Active Retrieval Augmented Generationcited by 516
  5. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 458
  6. 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 441
  7. 2020GeDi: Generative Discriminator Guided Sequence Generationcited by 378
  8. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Modelscited by 283
  9. 2025Why Language Models Hallucinatecited by 220
  10. 2024Corrective Retrieval Augmented Generationcited by 197
  11. 2019MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehensioncited by 184
  12. 2024ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLMcited by 73
  13. 2024Context-DPO: Aligning Language Models for Context-Faithfulnesscited by 50
  14. 2025Evaluating Scoring Bias in LLM-as-a-Judgecited by 43
  15. 2024RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processingcited by 25
  16. 2024SFR-RAG: Towards Contextually Faithful LLMscited by 19
  17. 2025SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compressioncited by 10
  18. 2025A Survey on Retrieval And Structuring Augmented Generation with Large Language Modelscited by 8
  19. 2025Influence Guided Context Selection for Effective Retrieval-Augmented Generationcited by 7
  20. 2025LTRR: Learning To Rank Retrievers for LLMscited by 4
  21. 2024Retrieval-Augmented Feature Generation for Domain-Specific Classificationcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Principled Context Engineering for RAG: Statistical Guarantees via Conformal Prediction
  2. 2026In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning
  3. 2026Reason and Verify: A Framework for Faithful Retrieval-Augmented Generation
  4. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  5. 2026Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict
  6. 2026Why Retrieval-Augmented Generation Fails: A Graph Perspective
  7. 2025Retrieval-augmented Decoding for Improving Truthfulness in Open-ended Generation
  8. 2025Grounding Long-Context Reasoning with Contextual Normalization for Retrieval-Augmented Generation