Why is plausibility surprisingly problematic as an XAI criterion?

• URL: http://arxiv.org/abs/2303.17707v3
• Date: Tue, 18 Jun 2024 22:38:32 GMT
• Title: Why is plausibility surprisingly problematic as an XAI criterion?
• Authors: Weina Jin, Xiaoxiao Li, Ghassan Hamarneh,
• Abstract summary: We conduct the first critical examination of a common XAI criterion: plausibility. It measures how convincing the AI explanation is to humans. We do not recommend using plausibility as a criterion to evaluate or optimize XAI algorithms.
• Score: 38.0428570713717
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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. XAI algorithms are designed to explain AI decisions in human-understandable ways. 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 the first critical examination of a common XAI criterion: plausibility. It measures how convincing the AI explanation is to humans, and is usually quantified by metrics on feature localization or correlation of feature attribution. Our examination shows, although plausible explanations can improve users' understanding and local trust in an AI decision, doing so is at the cost of abandoning other possible approaches of enhancing understandability, increasing misleading explanations that manipulate users, being unable to achieve complementary human-AI task performance, and deteriorating users' global trust in the overall AI system. Because the flaws outweigh the benefits, we do not recommend using plausibility as a criterion to evaluate or optimize XAI algorithms. We also identify new directions to improve XAI on understandability and utility to users including complementary human-AI task performance.

Related papers

• Investigating the Role of Explainability and AI Literacy in User Compliance [2.8623940003518156]
  We find that users' compliance increases with the introduction of XAI but is also affected by AI literacy. We also find that the relationships between AI literacy XAI and users' compliance are mediated by the users' mental model of AI.
  arXiv  Detail & Related papers  (2024-06-18T14:28:12Z)
• Seamful XAI: Operationalizing Seamful Design in Explainable AI [59.89011292395202]
  Mistakes in AI systems are inevitable, arising from both technical limitations and sociotechnical gaps. We propose that seamful design can foster AI explainability by revealing sociotechnical and infrastructural mismatches. We explore this process with 43 AI practitioners and real end-users.
  arXiv  Detail & Related papers  (2022-11-12T21:54:05Z)
• Regulating eXplainable Artificial Intelligence (XAI) May Harm Consumers [3.989227271669354]
  Common wisdom is that regulating AI by mandating fully transparent XAI leads to greater social welfare. Our paper challenges this notion through a game theoretic model of a policy-maker who maximizes social welfare. We study the notion of XAI fairness, which may be impossible to guarantee even under mandatory XAI.
  arXiv  Detail & Related papers  (2022-09-07T23:36:11Z)
• Transcending XAI Algorithm Boundaries through End-User-Inspired Design [27.864338632191608]
  Lacking explainability-focused functional support for end users may hinder the safe and responsible use of AI in high-stakes domains. Our work shows that grounding the technical problem in end users' use of XAI can inspire new research questions. Such end-user-inspired research questions have the potential to promote social good by democratizing AI and ensuring the responsible use of AI in critical domains.
  arXiv  Detail & Related papers  (2022-08-18T09:44:51Z)
• Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI [65.44737844681256]
  A lack of consensus on how to evaluate explainable AI (XAI) hinders the advancement of the field. We argue that one way to close the gap is to develop evaluation methods that account for different user requirements.
  arXiv  Detail & Related papers  (2022-06-22T05:17:33Z)
• Cybertrust: From Explainable to Actionable and Interpretable AI (AI2) [58.981120701284816]
  Actionable and Interpretable AI (AI2) will incorporate explicit quantifications and visualizations of user confidence in AI recommendations. It will allow examining and testing of AI system predictions to establish a basis for trust in the systems' decision making.
  arXiv  Detail & Related papers  (2022-01-26T18:53:09Z)
• A User-Centred Framework for Explainable Artificial Intelligence in Human-Robot Interaction [70.11080854486953]
  We propose a user-centred framework for XAI that focuses on its social-interactive aspect. The framework aims to provide a structure for interactive XAI solutions thought for non-expert users.
  arXiv  Detail & Related papers  (2021-09-27T09:56:23Z)
• Explainable Artificial Intelligence Approaches: A Survey [0.22940141855172028]
  Lack of explainability of a decision from an Artificial Intelligence based "black box" system/model is a key stumbling block for adopting AI in high stakes applications. We demonstrate popular Explainable Artificial Intelligence (XAI) methods with a mutual case study/task. We analyze for competitive advantages from multiple perspectives. We recommend paths towards responsible or human-centered AI using XAI as a medium.
  arXiv  Detail & Related papers  (2021-01-23T06:15:34Z)
• Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey [2.7086321720578623]
  Black-box nature of deep neural networks challenges its use in mission critical applications. XAI promotes a set of tools, techniques, and algorithms that can generate high-quality interpretable, intuitive, human-understandable explanations of AI decisions.
  arXiv  Detail & Related papers  (2020-06-16T02:58:10Z)
• Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making [53.62514158534574]
  We study whether features that reveal case-specific model information can calibrate trust and improve the joint performance of the human and AI. We show that confidence score can help calibrate people's trust in an AI model, but trust calibration alone is not sufficient to improve AI-assisted decision making.
  arXiv  Detail & Related papers  (2020-01-07T15:33:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.