mlsanityData to 7 Oct 2026

Investigating Human-Aligned Large Language Model Uncertainty

arXiv 2503.12528 ↗First posted 16 Mar 2025cs.CLcited by 2

On the map: LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment

Abstract (arXiv)

Recent work has sought to quantify large language model uncertainty to facilitate model control and modulate user trust. Previous works focus on measures of uncertainty that are theoretically grounded or reflect the average overt behavior of the model. In this work, we investigate a variety of uncertainty measures, in order to identify measures that correlate with human group-level uncertainty. We find that Bayesian measures and a variation on entropy measures, top-k entropy, tend to agree with human behavior as a function of model size. We find that some strong measures decrease in human-similarity with model size, but, by multiple linear regression, we find that combining multiple uncertainty measures provide comparable human-alignment with reduced size-dependency.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 31 of its 43 references that are in the map. First posted on arXiv 16 Mar 2025.

Builds on

31 of 43 references.

References · 31

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  6. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  7. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 946
  8. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 788
  9. 2023Whose Opinions Do Language Models Reflect?cited by 759
  10. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 737
  11. 2022Teaching Models to Express Their Uncertainty in Wordscited by 731
  12. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 439
19 more
  1. 2020Unsupervised Quality Estimation for Neural Machine Translationcited by 210
  2. 2021On Hallucination and Predictive Uncertainty in Conditional Language Generationcited by 176
  3. 2023Do LLMs exhibit human-like response biases? A case study in survey designcited by 176
  4. 2023Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthinesscited by 121
  5. 2023Decomposing Uncertainty for Large Language Models through Input Clarification Ensemblingcited by 113
  6. 2024What Large Language Models Know and What People Think They Knowcited by 109
  7. 2023Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Modelscited by 91
  8. 2024LUQ: Long-text Uncertainty Quantification for LLMscited by 79
  9. 2023LoRA ensembles for large language model fine-tuningcited by 65
  10. 2024Linguistic Calibration of Long-Form Generationscited by 59
  11. 2021Do language models learn typicality judgments from text?cited by 32
  12. 2024Finetuning Language Models to Emit Linguistic Expressions of Uncertaintycited by 25
  13. 2023How Powerful are Decoder-Only Transformer Neural Models?cited by 20
  14. 2024An Evaluation of Estimative Uncertainty in Large Language Modelscited by 13
  15. 2025How Many Human Survey Respondents is a Large Language Model Worth? An Uncertainty Quantification Perspectivecited by 10
  16. 2023Using Artificial Populations to Study Psychological Phenomena in Neural Modelscited by 8
  17. 2024Do Large Language Models Learn Human-Like Strategic Preferences?cited by 8
  18. 2024How Well Do Deep Learning Models Capture Human Concepts? The Case of the Typicality Effectcited by 7
  19. 2024Large Language Model Recall Uncertainty is Modulated by the Fan Effectcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Human-Alignment and Calibration of Inference-Time Uncertainty in Large Language Modelscited by 0
  2. 2026Human-Alignment, Calibration, and Activation Patterns in Large Language Model Uncertaintycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Understanding the Learning Dynamics of Alignment with Human Feedback
  2. 2023From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models
  3. 2024Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Models
  4. 2025Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges
  5. 2025Operationalizing Pluralistic Values in Large Language Model Alignment Reveals Trade-offs in Safety, Inclusivity, and Model Behavior
  6. 2024Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Function
  7. 2024Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models
  8. 2025Can Finetuing LLMs on Small Human Samples Increase Heterogeneity, Alignment, and Belief-Action Coherence?