paper-with-me

홈 › Papers

Beyond Satisfaction: From Placebic to Actionable Explanations For Enhanced Understandability

2025-12-06 · Joe Shymanski, Jacob Brue, Sandip Sen arxiv

Explainable AI (XAI) presents useful tools to facilitate transparency and trustworthiness in machine learning systems. However, current evaluations of system explainability often rely heavily on subjective user surveys, which may not adequately capture the effectiveness of explanations. This paper critiques the overreliance on user satisfaction metrics and explores whether these can differentiate between meaningful (actionable) and vacuous (placebic) explanations. In experiments involving optimal Social Security filing age selection tasks, participants used one of three protocols: no explanations, placebic explanations, and actionable explanations. Participants who received actionable explanations significantly outperformed the other groups in objective measures of their mental model, but users rated placebic and actionable explanations as equally satisfying. This suggests that subjective surveys alone fail to capture whether explanations truly support users in building useful domain understanding. We propose that future evaluations of agent explanation capabilities should integrate objective task performance metrics alongside subjective assessments to more accurately measure explanation quality. The code for this study can be found at https://github.com/Shymkis/social-security-explainer.

📄 PDF Abstract BibTeX arXiv:2512.06591

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Not All Explanations are Created Equal: Investigating the Pitfalls of Current XAI Evaluation

2025-09-27 · Joe Shymanski, Jacob Brue, Sandip Sen arxiv

Explainable Artificial Intelligence (XAI) aims to create transparency in modern AI models by offering explanations of the models to human users. There are many ways in which researchers have attempted to evaluate the qua…

Quality Without Usefulness: LLM-Generated XAI Narratives as Trust Heuristics Rather Than Decision Aids

2026-05-26 · Fabian Lukassen, Jan Herrmann, Christoph Weisser, Alexander Silbersdorff 외 arxiv

Prior work shows that Large Language Models (LLMs) can transform Explainable AI (XAI) outputs into Natural Language Explanations (NLEs) that score highly on quality metrics such as plausibility, coherence, and comprehens…

Out-of-Distribution Detection

A Two-Stage Algorithm for Cost-Efficient Multi-instance Counterfactual Explanations

2024-03-02 · André Artelt, Andreas Gregoriades

Counterfactual explanations constitute among the most popular methods for analyzing black-box systems since they can recommend cost-efficient and actionable changes to the input of a system to obtain the desired system o…

counterfactual

From Plausible to Actionable: A Position on LLM Self-Explanations

2026-07-17 · Elize Herrewijnen, Benedetta Muscato, Gizem Gezici, Fosca Giannotti arxiv

Large Language Models (LLMs) can generate natural language explanations that rationalize their own decisions, a phenomenon commonly referred to as self-explanations. Such explanations have emerged as a promising directio…

Justifying Social-Choice Mechanism Outcome for Improving Participant Satisfaction

2022-05-24 · Sharadhi Alape Suryanarayana, David Sarne, Sarit Kraus

In many social-choice mechanisms the resulting choice is not the most preferred one for some of the participants, thus the need for methods to justify the choice made in a way that improves the acceptance and satisfactio…