Bridging the Gap between Human-Computer Interaction and Machine-Learning on Explainable AI: Initial Observations and Lessons Learned

Explainability in artificial intelligence (XAI) is a rapidly growing research field nowadays, in particular in machine learning (ML). XAI concerns both the technical capacity to understand the functioning of ML models and the adequacy of the explanations with the targeted users and the contexts of use. It thus joins both the concerns of ML and of human-computer interaction (HCI) researchers. We therefore organized a workshop on XAI during the IHM’22 conference and gathered about thirty researchers from the HCI and ML communities. The contribution of this paper sums up the main teachings and the most promising avenues for collaboration that emerged during the discussions.