When LLM Rationales Become User-Facing: Effects on Trust Perception, Decision-Making, and Gaze Behaviors

2026-06-24

AI Summary

This study addresses the challenge of trust calibration in human–AI interaction caused by reasoning rationales generated by large language models (LLMs). Through two integrated studies combining online behavioral experiments and eye-tracking, the authors systematically investigate how rationale correctness, presentation format, and expressions of certainty influence users’ perceived trust, decision confidence, and cognitive load. The work proposes an auditable trust calibration framework and reveals that incorrect rationales, while reducing system credibility, lead users to scrutinize supporting evidence more closely—thereby challenging the common assumption that “more reasoning is better.” Furthermore, eye-tracking metrics effectively predict users’ trust states, offering empirical grounding for the design of trustworthy AI interfaces.

Abstract

Large language models (LLMs) increasingly show step-by-step reasoning rationales alongside their answers, turning reasoning from an internal model capability into a user-facing interface feature. Yet it is unclear whether such rationales help users judge when trust is warranted or merely persuade through fluent reasoning. We address this gap through the lens of auditable trust calibration: user-facing rationales should help people inspect whether an answer is warranted by evidence. We test this framing in factual verification through two linked studies. Study 1, an online experiment (N=68), manipulated rationale presentation format (instant, delayed, on demand), rationale correctness (correct, incorrect), and certainty framing (none, certain, uncertain). Study 2, a controlled eye-tracking study (N=54), examined how no-, correct-, and incorrect-rationale conditions were associated with users' trust, decision-making, and eye-movement patterns. Study 1 showed no reliable presentation-format effects; instead, rationale correctness and certainty framing influenced the trust in the information, trust in the LLM system, and decision confidence. In Study 2, incorrect rationales drew more attention to the supporting evidence and larger pupil diameter while the rationale was viewed, consistent with greater cognitive effort. Incorrect rationales also lowered trust in LLM system relative to showing no rationale, whereas the no-rationale difference was weaker for trust in information. A post-hoc predictive modeling analysis of gaze data from Study 2 further showed that gaze features carried predictive signal for trust- and decision-related user states. This work challenges the assumption that more reasoning is always better and supports rationale designs that are selective, linked to evidence, calibrated in how they express certainty, and easier to verify.

Problem

• trust calibration
• LLM rationales
• user-facing reasoning
• fact verification
• human-AI interaction

Innovation

• auditable trust calibration
• LLM rationales
• eye-tracking
• trust perception
• cognitive effort