Informative Semi-Factuals for XAI: The Elaborated Explanations that People Prefer
Saugat Aryal, Mark T. Keane

TL;DR
This paper introduces the informative semi-factuals (ISF) algorithm in XAI, which generates elaborated explanations by revealing hidden features influencing decisions, and demonstrates their effectiveness and user preference over simpler semi-factuals.
Contribution
The paper proposes the ISF algorithm that enhances semi-factual explanations with additional feature information, improving informativeness and user preference.
Findings
ISF produces high-quality, informative semi-factuals on benchmark datasets.
Users prefer elaborated explanations provided by ISF over simpler semi-factuals.
Experimental results confirm the effectiveness of the ISF method.
Abstract
Recently, in eXplainable AI (XAI), explanations -- so-called semi-factuals -- have emerged as a popular strategy that explains how a predicted outcome even when certain input-features are altered. For example, in the commonly-used banking app scenario, a semi-factual explanation could inform customers about better options, other alternatives for their successful application, by saying " you asked for double the loan amount, you would still be accepted". Most semi-factuals XAI algorithms focus on finding maximal value-changes to a single key-feature that do alter the outcome (unlike counterfactual explanations that often find minimal value-changes to several features that alter the outcome). However, no current semi-factual method explains these extreme value-changes do not alter outcomes;…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsExplainable Artificial Intelligence (XAI) · Multimodal Machine Learning Applications · Advanced Bandit Algorithms Research
