Addressing the Selection Problem in Explainable AI
Quick summary
arXiv:2608.22356v1 Announce Type: new Abstract: Explainable AI (XAI) research has produced a plethora of explanation techniques, yet user studies repeatedly show that available explanations are not effective in practice. We argue that, given the siloed nature of conventional XAI, users are struggling to select the appropriate XAI technique. Viewing XAI through a philosophical lens, we offer a formalization of what we call the selection problem: the systematic failure of XAI interfaces to bridge the gap between a user's natural-language uncertainty and the explanation technique that resolves it
Key takeaways
- arXiv:2608.22356v1 Announce Type: new Abstract: Explainable AI (XAI) research has produced a plethora of explanation techniques, yet user studies repeatedly show that available explanations are not effective in practice.
- We argue that, given the siloed nature of conventional XAI, users are struggling to select the appropriate XAI technique.
- Viewing XAI through a philosophical lens, we offer a formalization of what we call the selection problem: the systematic failure of XAI interfaces to bridge the gap between a user's natural-language uncertainty and the explanation technique that resolves it
Why it matters
“Addressing the Selection Problem in Explainable AI” highlights the need for repeatable measurement rather than a single impressive demonstration. Independent validation across datasets and clearly stated limitations determine whether a result can guide product decisions.
Member comments