mlsanityData to 14 Oct 2026

Epistemic Integrity in Large Language Models

arXiv 2411.06528 ↗First posted 10 Nov 2024cs.CL cs.AI cs.HCcited by 7

Not on the map. Why?

Abstract (arXiv)

Large language models are increasingly relied upon as sources of information, but their propensity for generating false or misleading statements with high confidence poses risks for users and society. In this paper, we confront the critical problem of epistemic miscalibration unicodex2013 where a model's linguistic assertiveness fails to reflect its true internal certainty. We introduce a new human-labeled dataset and a novel method for measuring the linguistic assertiveness of Large Language Models (LLMs) which cuts error rates by over 50% relative to previous benchmarks. Validated across multiple datasets, our method reveals a stark misalignment between how confidently models linguistically present information and their actual accuracy. Further human evaluations confirm the severity of this miscalibration. This evidence underscores the urgent risk of the overstated certainty LLMs hold which may mislead users on a massive scale. Our framework provides a crucial step forward in diagnosing this miscalibration, offering a path towards correcting it and more trustworthy AI across domains.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 24 of its 53 references that are in the map. First posted on arXiv 10 Nov 2024.

Builds on

24 of 53 references.

References · 24

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  3. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 974
  4. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 819
  5. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 752
  6. 2022Teaching Models to Express Their Uncertainty in Wordscited by 751
  7. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 742
  8. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 445
  9. 2020Calibration of Pre-trained Transformerscited by 315
  10. 2022Prompting GPT-3 To Be Reliablecited by 260
  11. 2020Reducing conversational agents' overconfidence through linguistic calibrationcited by 210
  12. 2023Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Modelscited by 150
12 more
  1. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 147
  2. 2024Taming Overconfidence in LLMs: Reward Calibration in RLHFcited by 112
  3. 2023R-Tuning: Instructing Large Language Models to Say `I Don't Know'cited by 111
  4. 2024Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertaintycited by 106
  5. 2023Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Modelscited by 91
  6. 2024Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?cited by 87
  7. 2024Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debatecited by 48
  8. 2023Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimationcited by 39
  9. 2021Measuring Sentence-Level and Aspect-Level (Un)certainty in Science Communicationscited by 27
  10. 2024Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigationcited by 19
  11. 2024Perceptions of Linguistic Uncertainty by Language Models and Humanscited by 15
  12. 2022Probing neural language models for understanding of words of estimative probabilitycited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 4.

7 papers.

  1. 2026Hallucinations Undermine Trust; Metacognition is a Way Forwardcited by 5
  2. 2026Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence?cited by 2
  3. 2025The Variance Paradox: How AI Reduces Diversity but Increases Noveltycited by 1
  4. 2026Safer Policy Compliance with Dynamic Epistemic Fallbackcited by 1
  5. 2025LLM Assertiveness can be Mechanistically Decomposed into Emotional and Logical Componentscited by 0
  6. 2025Stemming Hallucination in Language Models Using a Licensing Oraclecited by 0
  7. 2026Consistent but Miscalibrated: Evaluating LLM Limitations for Risk Communication in Natural Languagecited by 0