“very likely” Means “uncertain”? How LLMs Diverge from Humans in Linguistic Uncertainty Quantification
Jinhao Duan, Zicheng Liu, Zijie Liu, Kaidi Xu, Tianlong Chen
Abstract
Humans express uncertainty verbally via markers (e.g., "possible", "likely"), yet most LLM uncertainty quantification (UQ) relies on costing likelihood- or consistency-based signals. From a cognitive perspective, accurate verbal uncertainty reflects metacognitive monitoring, representing knowledge boundaries ("knowing that you don't know") to support regulation and information seeking. In this paper, we investigate: How LLMs diverge from humans in verbal uncertainty quantification? Can verbal markers reliably quantify LLM uncertainty? We curate a corpus of human uncertainty markers from psychology and decision-science literature and benchmark LLMs against it. We observe that LLMs encode verbal uncertainty with numerical levels that differ substantially from those of humans. We then introduce VOCAL, a novel optimization-based algorithm that learns an optimal uncertainty profile over uncertainty markers directly from LLM outputs. By fitting a marker–uncertainty mapping to best explain empirical correctness, VOCALdiscovers how much probability mass each verbal marker should convey, rather than estimating uncertainty via repeated sampling. VOCAL enables a direct, marker-level comparison of confidence semantics between humans and LLMs, disentangling mismatch and revealing systematic confidence disparities in verbal expressions.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs cites Language Models are Few-Shot Learners
- Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs cites Uncertainty Estimation in Autoregressive Structured Prediction
- PAL: Program-aided Language Models cites Language Models are Few-Shot Learners
- PAL: Program-aided Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Builds on22
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMsMiao Xiong, Zhiyuan Hu, Xinyang Lu, Yifei Li et al.ICLR 2024 · 867 citations
- PAL: Program-aided Language ModelsLuyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon et al.ICML 2023 · 700 citations
- Uncertainty Estimation in Autoregressive Structured PredictionAndrey Malinin, Mark J. F. GalesICLR 2021 · 439 citations
Related papers
- Representations of Fact, Fiction and Forecast in Large Language Models: Epistemics and AttitudesMeng Li, Michael Vrazitulis, David SchlangenACL 2025 · 1 citation
- From Sampling to Cognition: Modeling Internal Cognitive Confidence in Language Models for Robust Uncertainty CalibrationHao Li, Tao He, Jiafeng Liang, Zheng Chu et al.AAAI 2026
- MetaFaith: Faithful Natural Language Uncertainty Expression in LLMsGabrielle Kaili-May Liu, Gal Yona, Avi Caciularu, Idan Szpektor et al.EMNLP 2025
- Calibrating Verbal Uncertainty as a Linear Feature to Reduce HallucinationsZiwei Ji, Lei Yu, Yeskendir Koishekenov, Yejin Bang et al.EMNLP 2025 · 1 citation
- Perceptions of Linguistic Uncertainty by Language Models and HumansCatarina G. Belém, Markelle Kelly, Mark Steyvers, Sameer Singh et al.EMNLP 2024 · 6 citations
