mlsanityData to 14 Oct 2026

Can LLMs Take Retrieved Information with a Grain of Salt?

arXiv 2605.06919 ↗First posted 7 May 2026cs.CLcited by 0

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

Abstract (arXiv)

Large language models have demonstrated impressive retrieval-augmented capabilities. However, a crucial area remains underexplored: their ability to appropriately adapt responses to the certainty of the retrieved information. It is a limitation with real consequences in high-stakes domains like medicine and finance. We evaluate eight LLMs on their context-certainty obedience, measuring how well they adjust responses to match expressed context certainty. Our analysis reveals systematic limitations: LLMs struggle to recall prior knowledge after observing an uncertain context, misinterpret expressed certainties, and overtrust complex contexts. To address these, we propose an interaction strategy combining prior reminders, certainty recalibration, and context simplification. This approach reduces obedience errors by 25% on average, without modifying model weights, demonstrating the efficacy of interaction design in enhancing LLM reliability. Our contributions include a principled evaluation metric, empirical insights into LLMs' uncertainty handling, and a portable strategy to improve context-certainty obedience across diverse LLMs.

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 30 of its 34 references that are in the map. First posted on arXiv 7 May 2026.

Builds on

30 of 34 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation10 Jun
  2. 2025After Retrieval, Before Generation: Enhancing the Trustworthiness of Large Language Models in Retrieval-Augmented Generation21 May
  3. 2025Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models20 Mar
  4. 2025Uncertainty Quantification in Retrieval Augmented Question Answering25 Feb
  5. 2024To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts18 Oct
  6. 2024ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence16 Apr
  7. 2024Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models22 Feb

Other references · 23

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2024Qwen2.5 Technical Reportcited by 4,942
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  6. 2025Gemma 3 Technical Reportcited by 1,824
  7. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
  8. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,298
  9. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 938
  10. 2022Contrastive Decoding: Open-ended Text Generation as Optimizationcited by 609
  11. 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 327
  12. 2023A Survey of Confidence Estimation and Calibration in Large Language Modelscited by 256
11 more
  1. 2025Uncertainty Quantification and Confidence Calibration in Large Language Models: A Surveycited by 95
  2. 2020Language Models as Fact Checkers?cited by 51
  3. 2025LaMP-QA: A Benchmark for Personalized Long-form Question Answeringcited by 31
  4. 2025Accumulating Context Changes the Beliefs of Language Modelscited by 28
  5. 2021Not All Relevance Scores are Equal: Efficient Uncertainty and Calibration Modeling for Deep Retrieval Modelscited by 18
  6. 2024Do LLMs Play Dice? Exploring Probability Distribution Sampling in Large Language Models for Behavioral Simulationcited by 14
  7. 2025Exploring the Potential for Large Language Models to Demonstrate Rational Probabilistic Beliefscited by 9
  8. 2023Are Large Language Models Good Fact Checkers: A Preliminary Studycited by 8
  9. 2025Reasoning Under Uncertainty: Exploring Probabilistic Reasoning Capabilities of LLMscited by 8
  10. 2026Contradiction to Consensus: Dual Perspective, Multi Source Retrieval Based Claim Verification with Source Level Disagreement using LLMcited by 1
  11. 2026From Relevance to Authority: Authority-aware Generative Retrieval in Web Search Enginescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Interpreting and Mitigating Unwanted Uncertainty in LLMs
  2. 2026Certainty Is Not Just Correctness: Rethinking Token-Level Certainty in LLM Reasoning
  3. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
  4. 2024Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style
  5. 2026Beyond "I Don't Know": Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertainty
  6. 2026Not All Uncertainty Is Equal: How Uncertainty Granularity Shapes Human Verification in LLM-Assisted Decision Making ↗
  7. 2025Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Models
  8. 2025Accommodate Knowledge Conflicts in Retrieval-augmented LLMs: Towards Robust Response Generation in the Wild