ExplainabilityTransparencyTrustworthinesscs.AI
Interaction Design for Explainable AI: Workshop Proceedings
Prashan Madumal, Ronal Singh, Joshua Newn, Frank Vetere
December 13, 2018
arXiv.org
1 citations
Key Takeaways
-
Black-box AI decisions require justification: As AI systems make increasingly consequential decisions affecting individuals and society, there is an ethical imperative to explain how and why these decisions are made, rather than treating AI as an unexplainable "black box."
-
Current XAI research often ignores human needs: Much existing explainable AI research relies on researchers' assumptions about what makes a "good" explanation without actually considering how real users interact with these systems or what they need to understand them.
-
Human-centered design is essential for XAI: Effective explainability requires grounding AI explanations in interaction design and human factors—meaning researchers must study how people actually use and understand AI explanations, not just develop technical solutions in isolation.
-
XAI is fundamentally a design challenge: The workshop emphasizes that making AI explainable is not purely a technical problem but an interaction design problem that requires collaboration between AI researchers, HCI (human-computer interaction) specialists, and other fields focused on human needs.
Abstract
As artificial intelligence (AI) systems become increasingly complex and ubiquitous, these systems will be responsible for making decisions that directly affect individuals and society as a whole. Such decisions will need to be justified due to ethical concerns as well as trust, but achieving this has become difficult due to the `black-box' nature many AI models have adopted. Explainable AI (XAI) can potentially address this problem by explaining its actions, decisions and behaviours of the system to users. However, much research in XAI is done in a vacuum using only the researchers' intuition of what constitutes a `good' explanation while ignoring the interaction and the human aspect. This workshop invites researchers in the HCI community and related fields to have a discourse about human-centred approaches to XAI rooted in interaction and to shed light and spark discussion on interaction design challenges in XAI.