As humans we constantly act and speak so that implicitly or explicitly we make our intentions more understandable by others. This talk explores a number of ways in which this can also be possible in our interactions with computers in general and AI in particular. This includes coherence in explainable AI; epistemic interaction designed to give AI more information about users; human explanations in synergistic interactions with AI; and explainable user interfaces for non-AI human–computer interaction. Several of these topics have been developed as part of the TANGO EU Horizon project on hybrid human–AI decision making. Some are illustrated in prototypes; others are at conceptual state; all pose challenges and opportunities for future research.
Slides
Main sources
- Alan Dix, Ben Wilson, Matt Roach, Tommaso Turchi, and Alessio Malizia (2024).
Epistemic Interaction – tuning interfaces to provide information for AI support. SYNERGY Workshop @ AVI 2024 - 17th International Conference on Advanced Visual Interfaces, 3rd June 2024, Arenzano (Genoa), Italy.
more ... - A. Dix, T. Turchi, B. Wilson, A. Monreale and M. Roach. (2025).
Talking Back – human input and explanations to interactive AI systems. Workshop on Adaptive eXplainable AI (AXAI), IUI 2025, Cagliari, Italy, 24th March 2025.
more ... - A. Dix, T. Turchi, B. Wilson, A. Monreale and M. Roach. (2025).
Maintaining Coherence in Explainable AI: Strategies for Consistency Across Time and Interaction. SYNERGY – Designing and Building Hybrid Human–AI Systems || Workshop on Adaptive eXplainable AI (AXAI), HHAI 2025, Pisa, Italy, 9th June 2025.
more ... - A. Dix, T. Turchi and B. Wilson. (2025).
Towards Explainable User Interfaces. BCS HCI 2025. Cardiff, 9-11 Nov. 2025.
more ... - A. Dix (1992). Human issues in the use of pattern recognition techniques.
In Neural Networks and Pattern Recognition in Human Computer Interaction Eds. R. Beale and J. Finlay. Ellis Horwood. 429-451. (probably the first paper to highlight the dangers of ethnic, gender and socio-economic bias in black-box machine learning and propose transparency/explainability as a way to counter this.)
more ...
|
Artificial Intelligence: humans at the heart of algorithms
