Do Expressions Change Decisions? Exploring the Impact of AI's Explanation Tone on Decision-Making

2025-02-27

AI Summary

This study investigates how AI explanation tone—formal versus humorous—affects human decision-making, with emphasis on interactions among AI role (assistant, second-opinion provider, or expert), user attributes (e.g., age, extraversion), and contextual factors. Using large language models to generate tone-varied explanations, the research employs controlled behavioral experiments, objective decision metrics, and open-ended qualitative analysis. Results reveal that tone effects are highly context- and user-dependent: impact is strongest in second-opinion scenarios; older adults exhibit greater susceptibility to tone manipulation; and highly extraverted users demonstrate systematic perception biases. The study introduces two empirically grounded design principles—“tone consistency” (aligning explanation tone with AI role and task criticality) and “ethical alignment” (adapting tone to user characteristics while preserving transparency and fairness)—thereby advancing evidence-based guidelines for trustworthy, human-centered XAI interfaces.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability
• Knowledge Representation and Reasoning: Preferences

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems

Abstract

Explanatory information helps users to evaluate the suggestions offered by AI-driven decision support systems. With large language models, adjusting explanation expressions has become much easier. However, how these expressions influence human decision-making remains largely unexplored. This study investigated the effect of explanation tone (e.g., formal or humorous) on decision-making, focusing on AI roles and user attributes. We conducted user experiments across three scenarios depending on AI roles (assistant, second-opinion provider, and expert) using datasets designed with varying tones. The results revealed that tone significantly influenced decision-making regardless of user attributes in the second-opinion scenario, whereas its impact varied by user attributes in the assistant and expert scenarios. In addition, older users were more influenced by tone, and highly extroverted users exhibited discrepancies between their perceptions and decisions. Furthermore, open-ended questionnaires highlighted that users expect tone adjustments to enhance their experience while emphasizing the importance of tone consistency and ethical considerations. Our findings provide crucial insights into the design of explanation expressions.

Problem

• Impact of AI's explanation tone on decision-making
• Influence of user attributes on tone effectiveness
• User expectations for tone adjustments in AI explanations

Innovation

• AI explanation tone
• user decision impact
• tone adjustment design