Seeing the Reasoning: How LLM Rationales Influence User Trust and Decision-Making in Factual Verification Tasks

TL;DR

This study investigates how different presentation styles and cues in LLM rationales affect user trust, decision confidence, and reliance in factual verification, revealing that correctness and certainty cues significantly influence user perceptions.

Contribution

It provides empirical evidence on how rationale presentation and cues impact user trust and decision-making, highlighting design considerations for user-facing LLM explanations.

Findings

Correct rationales increase trust and confidence.

Certainty cues boost AI advice adoption.

Presentation format has minimal impact.

Abstract

Large Language Models (LLMs) increasingly show reasoning rationales alongside their answers, turning "reasoning" into a user-interface element. While step-by-step rationales are typically associated with model performance, how they influence users' trust and decision-making in factual verification tasks remains unclear. We ran an online study (N=68) manipulating three properties of LLM reasoning rationales: presentation format (instant vs. delayed vs. on-demand), correctness (correct vs. incorrect), and certainty framing (none vs. certain vs. uncertain). We found that correct rationales and certainty cues increased trust, decision confidence, and AI advice adoption, whereas uncertainty cues reduced them. Presentation format did not have a significant effect, suggesting users were less sensitive to how reasoning was revealed than to its reliability. Participants indicated they use rationales to primarily audit outputs and calibrate trust, where they expected rationales in stepwise, adaptive forms with certainty indicators. Our work shows that user-facing rationales, if poorly designed, can both support decision-making yet miscalibrate trust.