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

Aug 5, 2026

Explainability in artificial intelligence (XAI) is a fast-growing research area connecting machine-learning (ML) needs with human-computer interaction (HCI) concerns. XAI addresses both the technical ability to understand ML model behavior and the suitability of explanations for target users and application contexts. To capture these interactions, a workshop on XAI was organized during IHM’22, bringing together about thirty researchers from HCI and ML communities. The paper synthesizes key lessons and promising directions for collaboration.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Introduction

XAI goals and motivations

Workshop contribution and collaboration direction

Institutional Repository-Research Portal Dépôt Institutionnel-Portail de la Recherche University of easr[chportal.unamur.be](chportal.unamur.be) RESEARCH OUTPUTS / RÉSULTATS DE RECHERCHE Bridging the Gap between Human-Computer Interaction and Machine-Learning on Explainable AI Albert, Julien; Bibal, Adrien; Frénay, Benoît; Dumas, Bruno Published in: IHM'23-34e Conférence Internationale Francophone sur l'Interaction Humain-Machine Publication date: 2023 Document Version Publisher's PDF, also known as Version of record Link to publication Citation for pulished version (HARVARD): Albert, J, Bibal, A, Frénay, B & Dumas, B 2023, Bridging the Gap between Human-Computer Interaction and Machine-Learning on Explainable AI: Initial Observations and Lessons Learned. in IHM'23-34e Conférence Internationale Francophone sur l'Interaction Humain-Machine. General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. • Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal ? Take down policy If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim. Download date: 29. Nov. 2023 Bridging the Gap between Human-Computer Interaction and Machine-Learning on Explainable AI: Initial Observations and Lessons Learned Combler la distance entre l’interaction humain-machine et le machine learning sur l’IA explicable : premières observations et leçons apprises JULIEN ALBERT, NaDI/PReCISE, Faculty of Computer Science, University of Namur, Belgium ADRIEN BIBAL, University of Colorado Anschutz Medical Campus, USA BENOÎT FRENAY, NaDI/PReCISE, Faculty of Computer Science, University of Namur, Belgium BRUNO DUMAS, NaDI/PReCISE, Faculty of Computer Science, University of Namur, Belgium 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. CCS Concepts: • Human-centered computing → Human computer interaction (HCI); • Computing methodologies → Machine learning. Additional Key Words and Phrases: explainable artificial intelligence, machine learning, human-computer interaction L’explicabilité en intelligence artificielle (XAI) est un domaine de recherche en plein essor aujourd’hui, en particulier en machine learning (ML) . Ce domaine concerne à la fois la capacité technique à comprendre le fonctionnement des modèles de ML et l’adéquation des explications avec les utilisateurs et les contextes d’utilisation ciblés. Il rejoint ainsi les préoccupations des chercheurs à la fois en ML et en interaction humain-machine (IHM) . Nous avons donc organisé un atelier sur l’XAI pendant la conférence IHM’22 et avonsréuni une trentaine de chercheurs issus des communautés IHM et ML. La contribution de ce présent article résume les principaux enseignements et les pistes de collaboration les plus prometteuses qui ont émergé l

FAQs

What does explainable AI (XAI) aim to achieve in this work?

It develops methods and tools to explain AI systems in understandable terms for humans. It also targets transparency and trust concerns.

Why is XAI positioned at the intersection of ML and HCI?

XAI covers both understanding how ML models work and ensuring explanations match users and the contexts where they are used.

How did the authors gather insights for their paper?

They organized an XAI workshop during IHM’22 and brought together about thirty researchers from the HCI and ML communities.

Aug 5, 2026

Upload by Olivia Brown