When Hedging Hides Heterogeneity: A Measurement and Identification Framework for Uncertainty in Large Language Models

Abstract Large language models routinely hedge on contested questions, but the surface uniformity of such hedging conceals a heterogeneous mixture of underlying latent drivers. We distinguish four latent drivers: epistemic uncertainty, hermeneutic openness, alignment-induced policy effects (which can suppress or amplify evaluative stance), and cross-context interpretive divergence. We argue that verbalised output is best understood as a measurement-and-identification problem in which these heterogeneous latent drivers of uncertainty and stance are compressed into a single output channel by a noninjective verbalisation map: similar hedging or balancing language may reflect genuine uncertainty or instead policy and contextual effects, and a user cannot reliably distinguish these drivers from a single output. We formalise this compression, characterise the decision-theoretic regret of conflating drivers whose appropriate downstream interventions differ, and observe that this regret does not vanish under additional factual evidence when the dominant driver is non-epistemic. Empirical claims are anchored in a pre-specified replication study. We then introduce four families of identifying probes, namely factual-evidence augmentation, counterfactual rephrasing, standpoint-conditioned elicitation, and cross-lingual consistency, which provide directional identification of the dominant latent driver of an observed hedge. We close with implications for professional practice in journalism, policy analysis, and comparative research; design principles for uncertainty-disclosure interfaces; and a benchmark proposal for driver-stratified evaluation of LLM uncertainty.

Authors

Institutions

Publication Details

Journal
RSS Data Science and Artificial Intelligence
Published
2026-11-12
DOI
https://doi.org/10.1093/rssdat/udag004
Primary Topic
Ethics and Social Impacts of AI
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

When Hedging Hides Heterogeneity: A Measurement and Identification Framework for Uncertainty in Large Language Models

Yao Zhao
RSS Data Science and Artificial Intelligence
Ethics and Social Impacts of AI
article

When Hedging Hides Heterogeneity: A Measurement and Identification Framework for Uncertainty in Large Language Models

Yao Zhao
article en

Abstract

Abstract Large language models routinely hedge on contested questions, but the surface uniformity of such hedging conceals a heterogeneous mixture of underlying latent drivers. We distinguish four latent drivers: epistemic uncertainty, hermeneutic openness, alignment-induced policy effects (which can suppress or amplify evaluative stance), and cross-context interpretive divergence. We argue that verbalised output is best understood as a measurement-and-identification problem in which these heterogeneous latent drivers of uncertainty and stance are compressed into a single output channel by a noninjective verbalisation map: similar hedging or balancing language may reflect genuine uncertainty or instead policy and contextual effects, and a user cannot reliably distinguish these drivers from a single output. We formalise this compression, characterise the decision-theoretic regret of conflating drivers whose appropriate downstream interventions differ, and observe that this regret does not vanish under additional factual evidence when the dominant driver is non-epistemic. Empirical claims are anchored in a pre-specified replication study. We then introduce four families of identifying probes, namely factual-evidence augmentation, counterfactual rephrasing, standpoint-conditioned elicitation, and cross-lingual consistency, which provide directional identification of the dominant latent driver of an observed hedge. We close with implications for professional practice in journalism, policy analysis, and comparative research; design principles for uncertainty-disclosure interfaces; and a benchmark proposal for driver-stratified evaluation of LLM uncertainty.

RSS Data Science and Artificial Intelligence
Temple University (US)
Ethics and Social Impacts of AI
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon