Human-Alignment, Calibration, and Activation Patterns in Large Language Model Uncertainty

• URL: http://arxiv.org/abs/2605.30675v1
• Date: Fri, 29 May 2026 00:08:59 GMT
• Title: Human-Alignment, Calibration, and Activation Patterns in Large Language Model Uncertainty
• Abstract summary: We investigate the underexplored question of how similar large language model uncertainty is to human uncertainty.<n>We identify whether the models show evidence of simultaneous alignment and calibration on a variety of datasets.
• Score: 3.070121019787871
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Uncertainty Quantification is a large and growing subfield of large language model behavioral analysis. Primarily to recognize and combat hallucination, the field has largely focused on measuring and improving calibration, the accuracy of uncertainty judgments to task efficacy. In this work, we investigate the relatively underexplored question of how similar large language model uncertainty is to human uncertainty. We investigate the presence and strength of human-similar uncertainty signals, deemed uncertainty alignment, in large language model overt behavior and internal activation patterns. We identify whether the models show evidence of simultaneous alignment and calibration on a variety of datasets covering both multiple choice and open ended factual recall. And we characterize the effect of instruct fine-tuning on each of these facets.

Related papers

• Aligning LLM Uncertainty with Human Disagreement in Subjectivity Analysis [57.78407973423517]
  We advocate uncertainty-aware subjectivity analysis, where models are expected to make predictions while expressing uncertainty that reflects human disagreement.<n>To operationalize this perspective, we propose a two-phase Disagreement Perception and Uncertainty Alignment framework.<n> Experiments on three subjectivity analysis tasks show that DPUA preserves task performance while better aligning model uncertainty with human disagreement.
  arXiv  Detail & Related papers  (2026-05-11T11:52:58Z)
• Uncertainty-Aware Exploratory Direct Preference Optimization for Multimodal Large Language Models [53.15468578562038]
  We propose an Uncertainty-aware Exploratory Direct Preference Optimization (UE-DPO) method for Multimodal Large Language Models (MLLMs)<n>We first quantify the uncertainty from the model's failure to ground token predictions in the given image.<n>We then encourage more learning pressure on visually deficient tokens in preferred samples, and alleviate the over-penalization of beneficial knowledge in dispreferred samples.
  arXiv  Detail & Related papers  (2026-05-06T13:08:12Z)
• Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models [54.041320081289996]
  We present the first systematic empirical study of uncertainty estimation in audio-aware large language models (ALLMs)<n>We benchmark five representative methods, including predictive entropy, length-normalized entropy, semantic entropy, discrete semantic entropy, and P(True)<n>Our results reveal two key findings. First, semantic-level and verification-based methods consistently outperform token-level baselines on general audio reasoning benchmarks.
  arXiv  Detail & Related papers  (2026-04-28T12:56:22Z)
• Sensitivity Uncertainty Alignment in Large Language Models [0.0]
  We propose a framework for analyzing failures of large language models under adversarial and ambiguous inputs.<n>We define a scalar score, SUA_theta(x), capturing the difference between distributional sensitivity and predictive entropy.<n>We introduce SUA-TR, a training method combining consistency regularization and entropy alignment, along with an abstention rule for safer inference.
  arXiv  Detail & Related papers  (2026-04-21T17:53:12Z)
• Reasoning aligns language models to human cognition [12.07126784684808]
  We introduce an active probabilistic reasoning task that cleanly separates sampling (actively acquiring evidence) from inference (integrating evidence toward a decision)<n> Benchmarking humans and a broad set of contemporary large language models against near-optimal reference policies reveals a consistent pattern.<n>This model places humans and models in a shared low-dimensional cognitive space, reproduces behavioral signatures across agents, and shows how chain-of-thought shifts language models toward human-like regimes of evidence accumulation and belief-to-choice mapping.
  arXiv  Detail & Related papers  (2026-02-09T14:13:39Z)
• From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models [77.04403907729738]
  This survey charts the evolution of uncertainty from a passive diagnostic metric to an active control signal guiding real-time model behavior.<n>We demonstrate how uncertainty is leveraged as an active control signal across three frontiers.<n>This survey argues that mastering the new trend of uncertainty is essential for building the next generation of scalable, reliable, and trustworthy AI.
  arXiv  Detail & Related papers  (2026-01-22T06:21:31Z)
• Human-Alignment and Calibration of Inference-Time Uncertainty in Large Language Models [0.0]
  We evaluate a collection of inference-time uncertainty measures to determine how closely they align with both human group-level uncertainty and traditional notions of model calibration.<n>We find that numerous measures show evidence of strong alignment to human uncertainty, even despite the lack of alignment to human answer preference.
  arXiv  Detail & Related papers  (2025-08-11T17:22:45Z)
• Investigating Human-Aligned Large Language Model Uncertainty [0.0]
  We investigate a variety of uncertainty measures, in order to identify measures that correlate with human group-level uncertainty.<n>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.<n>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.
  arXiv  Detail & Related papers  (2025-03-16T14:45:43Z)
• On Subjective Uncertainty Quantification and Calibration in Natural Language Generation [2.622066970118316]
  Large language models often involve the generation of free-form responses, in which case uncertainty quantification becomes challenging. This work addresses these challenges from a perspective of Bayesian decision theory. We discuss how this assumption enables principled quantification of the model's subjective uncertainty and its calibration. The proposed methods can be applied to black-box language models.
  arXiv  Detail & Related papers  (2024-06-07T18:54:40Z)
• Investigating the Impact of Model Instability on Explanations and Uncertainty [43.254616360807496]
  We simulate uncertainty in text input by introducing noise at inference time. We find that high uncertainty doesn't necessarily imply low explanation plausibility. This suggests that noise-augmented models may be better at identifying salient tokens when uncertain.
  arXiv  Detail & Related papers  (2024-02-20T13:41:21Z)
• Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learning [76.98542249776257]
  Large-scale language models often face the challenge of "hallucination" We introduce an uncertainty-aware in-context learning framework to empower the model to enhance or reject its output in response to uncertainty.
  arXiv  Detail & Related papers  (2023-10-07T12:06:53Z)
• Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Models [74.07684768317705]
  LMs are highly sensitive to markers of certainty in prompts, with accuies varying more than 80%. We find that expressions of high certainty result in a decrease in accuracy as compared to low expressions; similarly, factive verbs hurt performance, while evidentials benefit performance. These associations may suggest that LMs is based on observed language use, rather than truly reflecting uncertainty.
  arXiv  Detail & Related papers  (2023-02-26T23:46:29Z)
• How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering [80.82194311274694]
  We examine the question "how can we know when language models know, with confidence, the answer to a particular query?" We examine three strong generative models -- T5, BART, and GPT-2 -- and study whether their probabilities on QA tasks are well calibrated. We then examine methods to calibrate such models to make their confidence scores correlate better with the likelihood of correctness.
  arXiv  Detail & Related papers  (2020-12-02T03:53:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.