mlsanityData to 7 Oct 2026

Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?

arXiv 2405.16908 ↗First posted 27 May 2024cs.CLcited by 85

Not on the map. Why?

Abstract (arXiv)

We posit that large language models (LLMs) should be capable of expressing their intrinsic uncertainty in natural language. For example, if the LLM is equally likely to output two contradicting answers to the same question, then its generated response should reflect this uncertainty by hedging its answer (e.g., "I'm not sure, but I think..."). We formalize faithful response uncertainty based on the gap between the model's intrinsic confidence in the assertions it makes and the decisiveness by which they are conveyed. This example-level metric reliably indicates whether the model reflects its uncertainty, as it penalizes both excessive and insufficient hedging. We evaluate a variety of aligned LLMs at faithfully communicating uncertainty on several knowledge-intensive question answering tasks. Our results provide strong evidence that modern LLMs are poor at faithfully conveying their uncertainty, and that better alignment is necessary to improve their trustworthiness.

Key facts. Cited by 85 papers in the map (data through 7 Oct 2026). Builds on 27 of its 53 references that are in the map. First posted on arXiv 27 May 2024.

Builds on

27 of 53 references.

References · 27

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2017On Calibration of Modern Neural Networkscited by 4,860
  3. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  4. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  5. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  6. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  7. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,122
  8. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  9. 2017Selective Classification for Deep Neural Networkscited by 799
  10. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 788
  11. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 733
  12. 2022Teaching Models to Express Their Uncertainty in Wordscited by 731
15 more
  1. 2023The Internal State of an LLM Knows When It's Lyingcited by 644
  2. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 385
  3. 2021True Few-Shot Learning with Language Modelscited by 343
  4. 2020Selective Question Answering under Domain Shiftcited by 228
  5. 2024Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?cited by 227
  6. 2023Fine-tuning Language Models for Factualitycited by 219
  7. 2024Many-Shot In-Context Learningcited by 203
  8. 2024In-Context Learning with Long-Context Models: An In-Depth Explorationcited by 126
  9. 2024Unfamiliar Finetuning Examples Control How Language Models Hallucinatecited by 85
  10. 2024Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluationcited by 79
  11. 2024Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedbackcited by 64
  12. 2023Uncertainty in Natural Language Generation: From Theory to Applicationscited by 61
  13. 2023What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variabilitycited by 51
  14. 2024Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answerscited by 18
  15. 2024LLMs can learn self-restraint through iterative self-reflectioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 10; 2025: 37; 2026: 38.

85 papers.

Sort:

By area:

  1. 2024LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinationscited by 230
  2. 2024A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directionscited by 115
  3. 2024Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Modelscited by 114
  4. 2024Learning to Route LLMs with Confidence Tokenscited by 66
  5. 2024Internal Consistency and Self-Feedback in Large Language Models: A Surveycited by 49
  6. 2025Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinationscited by 48
  7. 2024SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generationcited by 40
  8. 2025Generalization Bias in Large Language Model Summarization of Scientific Researchcited by 30
  9. 2025Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agentscited by 27
  10. 2025Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Predictioncited by 26
  11. 2025Revisiting Uncertainty Estimation and Calibration of Large Language Modelscited by 22
  12. 2024A Survey on the Honesty of Large Language Modelscited by 21
38 more
  1. 2025From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centeredcited by 21
  2. 2025DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMscited by 21
  3. 2025An Empirical Analysis of Uncertainty in Large Language Model Evaluationscited by 20
  4. 2025Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?cited by 16
  5. 2024Perceptions of Linguistic Uncertainty by Language Models and Humanscited by 15
  6. 2025MetaFaith: Faithful Natural Language Uncertainty Expression in LLMscited by 15
  7. 2026Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunitiescited by 15
  8. 2025Don't lie to your friends: Learning what you know from collaborative self-playcited by 14
  9. 2025Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Deliverycited by 14
  10. 2025Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missingcited by 14
  11. 2026Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAGcited by 14
  12. 2024From Loops to Oops: Fallback Behaviors of Language Models Under Uncertaintycited by 13
  13. 2026Diagnosing the Reliability of LLM-as-a-Judge via Item Response Theorycited by 13
  14. 2025Detecting (Un)answerability in Large Language Models with Linear Directionscited by 12
  15. 2026BAGEN: Are LLM Agents Budget-Aware?cited by 12
  16. 2026Can LLMs Introspect? A Reality Checkcited by 8
  17. 2024Epistemic Integrity in Large Language Modelscited by 7
  18. 2025Line of Duty: Evaluating LLM Self-Knowledge via Consistency in Feasibility Boundariescited by 7
  19. 2025Teaching Language Models to Faithfully Express their Uncertaintycited by 7
  20. 2025SelfReflect: Can LLMs Communicate Their Internal Answer Distribution?cited by 6
  21. 2025Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Modelscited by 6
  22. 2025Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learningcited by 6
  23. 2025HACK: Hallucinations Along Certainty and Knowledge Axescited by 6
  24. 2026LLMs Should Express Uncertainty Explicitlycited by 6
  25. 2025FESTA: Functionally Equivalent Sampling for Trust Assessment of Multimodal LLMscited by 5
  26. 2025Can Large Language Models Express Uncertainty Like Human?cited by 5
  27. 2025Generalization of Fine-Tuned Uncertainty Communication and Metacognition in Large Language Modelscited by 4
  28. 2026Equal Access, Unequal Interaction: A Counterfactual Audit of LLM Fairnesscited by 4
  29. 2026Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMscited by 4
  30. 2026Hallucinations Undermine Trust; Metacognition is a Way Forwardcited by 4
  31. 2025Preventing Rogue Agents Improves Multi-Agent Collaborationcited by 3
  32. 2025Towards Reliable Large Audio Language Modelcited by 3
  33. 2025Representations of Fact, Fiction and Forecast in Large Language Models: Epistemics and Attitudescited by 3
  34. 2025Language Model Guided Reinforcement Learning in Quantitative Tradingcited by 3
  35. 2025Stop Before You Fail: Operational Capability Boundaries for Mitigating Unproductive Reasoning in Large Reasoning Modelscited by 3
  36. 2025The Narrative Continuity Test: A Conceptual Framework for Evaluating Identity Persistence in AI Systemscited by 3
  37. 2025"It's trained by non-disabled people": Evaluating How Image Quality Affects Product Captioning with Vision-Language Modelscited by 3
  38. 2026Next Generation Active Learning: Mixture of LLMs in the Loopcited by 3

50 most cited of 85 All 85 (JSON)