How Humans and LLMs Differ in Processing Uncertainty in Polarized Discourse
Donkers, T., & Ziegler, J. (2026). In Association for Computing Machinery (ACM) (Ed.), Proceedings of the 34th ACM Conference on User Modeling, Adaptation and Personalization (UMAP ’26) (pp. 70–78). ACM.
Abstract
When people express uncertainty in online discourse (hedging claims, acknowledging limitations, or questioning their own positions), does this shape how others perceive the conversation? And can LLMs detect these social signals the way humans do? We address these questions by comparing human (N = 122) and LLM assessments of identical AI-generated social media posts about Universal Basic Income. To enable direct paired comparison, we developed calibrated “mirror personas” that replicate individual participants’ rating tendencies. Both rater types reliably distinguished polarized from moderate discourse across four constructs (uncertainty, emotionality, group salience, perceived polarization), though LLMs amplified condition differences by over sixfold in the most extreme cases, with the degree of amplification varying by construct and model family. Crucially, structural equation modeling revealed divergent processing architectures: humans exhibited integrative processing where perceived uncertainty directly reduced perceived polarization, even when messages varied in emotionality. This pattern, consistent with dual-process theories where uncertainty signals trigger deliberative evaluation, was absent in LLMs, which processed each construct independently without cross-dimensional mediation. Cross-validation confirmed this architectural difference. These findings suggest that expressed uncertainty serves a social function in human discourse comprehension, dampening polarization judgments in ways that current LLMs do not replicate. For AI-mediated communication systems, this gap implies that simply detecting uncertainty is insufficient; the challenge lies in modeling how uncertainty reshapes interpretation of the broader message.