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

arXiv: https://arxiv.org/abs/2603.07306 · HTML: https://mlsanity.com/paper/2603.07306/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 10 of its 33 references that are in the map.
- First posted on arXiv 7 Mar 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 10 of 10)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models](https://mlsanity.com/paper/2501.09686/) (2025)
- ["How do I fool you?": Manipulating User Trust via Misleading Black Box Explanations](https://mlsanity.com/paper/1911.06473/) (2019)
- [Explanations Can Reduce Overreliance on AI Systems During Decision-Making](https://mlsanity.com/paper/2212.06823/) (2022)
- [How model accuracy and explanation fidelity influence user trust](https://mlsanity.com/paper/1907.12652/) (2019)
- [Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs](https://mlsanity.com/paper/2305.14279/) (2023)
- [Reasoning Models Will Sometimes Lie About Their Reasoning](https://mlsanity.com/paper/2601.07663/) (2026)
- [Do You Trust What You See? Toward A Multidimensional Measure of Trust in Visualization](https://mlsanity.com/paper/2308.04727/) (2023)

## Built on by (most cited first, 1 of 1)

- [Design Theater: Evaluating the Gap Between User-Facing Design Reasoning and Implementation in Generative UI Tools](https://mlsanity.com/paper/2607.22928/) (2026)

## Abstract (arXiv)

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.