Rhetorical XAI: Explaining AI's Benefits as well as its Use via Rhetorical Design

2025-05-14

AI Summary

Explainable AI (XAI) systems often fail to effectively enhance user trust and adoption, as their explanations lack persuasive efficacy. Method: This study systematically integrates classical rhetoric—logos (logic), ethos (credibility), and pathos (emotion)—into XAI design, proposing the first tri-dimensional analytical framework that bridges rhetorical theory with human-AI interaction practice. Through rhetorical text analysis, mapping of XAI strategies onto rhetorical appeals, and empirical user evaluation, actionable design principles are derived. Contribution/Results: Rhetorically grounded explanations significantly improve users’ perceived AI utility and credibility, strengthen trust formation, and enhance human-AI collaboration quality. The work also identifies critical challenges in ensuring explanation authenticity, user-specific adaptability, and cross-context generalizability of rhetorical integration. By advancing XAI from mere intelligibility toward genuine acceptance, this research provides both theoretical foundations and practical design guidelines for persuasive, human-centered explainability.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability
• Machine Learning: Transparent, Interpretable, Explainable ML

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
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

This paper explores potential benefits of incorporating Rhetorical Design into the design of Explainable Artificial Intelligence (XAI) systems. While XAI is traditionally framed around explaining individual predictions or overall system behavior, explanations also function as a form of argumentation, shaping how users evaluate system perceived usefulness, credibility, and foster appropriate trust. Rhetorical Design offers a useful framework to analyze the communicative role of explanations between AI systems and users, focusing on: (1) logical reasoning conveyed through different types of explanations, (2) credibility projected by the system and its developers, and (3) emotional resonance elicited in users. Together, these rhetorical appeals help us understand how explanations influence user perceptions and facilitate AI adoption. This paper synthesizes design strategies from prior XAI work that align with these three rhetorical appeals and highlights both opportunities and challenges of integrating rhetorical design into XAI design.

Problem

• Incorporating Rhetorical Design into XAI systems
• Explaining AI benefits and use via argumentation
• Enhancing user trust through rhetorical appeals

Innovation

• Incorporates Rhetorical Design in XAI systems
• Focuses on logical reasoning, credibility, emotional resonance
• Synthesizes design strategies from prior XAI work