Why is plausibility surprisingly problematic as an XAI criterion?

2023-03-30

AI Summary

This paper critically exposes theoretical flaws and ethical risks inherent in “plausibility” as a core evaluation criterion for eXplainable Artificial Intelligence (XAI): it substitutes human intuition for logical and causal validity, thereby inducing explanation distortion, trust erosion, and breakdown of human-AI collaboration. Through conceptual analysis, philosophical argumentation, and methodological critique of existing evaluation frameworks, the paper systematically demonstrates—novelly—that plausibility lacks scientific grounding for measuring explanatory validity and possesses no normative foundation. It advocates abandoning plausibility as a criterion and proposes a new XAI evaluation paradigm anchored in three pillars: **causal soundness**, **user cognitive fit**, and **task utility enhancement**. Furthermore, it introduces a human-AI complementary efficacy modeling framework. The work aims to shift XAI evaluation from superficial acceptability toward substantively justified trust, fostering a more rigorous, responsible, and consensus-driven assessment standard for the field.

Abstract

Explainable artificial intelligence (XAI) is motivated by the problem of making AI predictions understandable, transparent, and responsible, as AI becomes increasingly impactful in society and high-stakes domains. The evaluation and optimization criteria of XAI are gatekeepers for XAI algorithms to achieve their expected goals and should withstand rigorous inspection. To improve the scientific rigor of XAI, we conduct a critical examination of a common XAI criterion: plausibility. Plausibility assesses how convincing the AI explanation is to humans, and is usually quantified by metrics of feature localization or feature correlation. Our examination shows that plausibility is invalid to measure explainability, and human explanations are not the ground truth for XAI, because doing so ignores the necessary assumptions underpinning an explanation. Our examination further reveals the consequences of using plausibility as an XAI criterion, including increasing misleading explanations that manipulate users, deteriorating users' trust in the AI system, undermining human autonomy, being unable to achieve complementary human-AI task performance, and abandoning other possible approaches of enhancing understandability. Due to the invalidity of measurements and the unethical issues, this position paper argues that the community should stop using plausibility as a criterion for the evaluation and optimization of XAI algorithms. We also delineate new research approaches to improve XAI in trustworthiness, understandability, and utility to users, including complementary human-AI task performance.

Problem

• Plausibility is invalid for measuring AI explainability
• Human explanations are not ground truth for XAI
• Plausibility criterion leads to misleading and unethical outcomes

Innovation

• Critically examines plausibility in XAI
• Rejects plausibility as invalid criterion
• Proposes new trustworthy XAI approaches