AI systems are increasingly used to make consequential decisions in a wide range of domains, including finance, healthcare and law. As a result, it is crucial to be able to explain the decisions of these systems, with the aim to deliver explainable AI (XAI) solutions suitable for a human-centred world.

Currently, methods for explainability are frequently one-off, developed and evaluated under the assumption that users will make a single query, and ignoring possible effects of multiple queries and feedback by the user. An alternative view of explanations is to take into account the continuous interplay between users and machines. In this view, explanations should be seen as interactive processes operating on objects which can be contested or futher elaborated. This view is particularly highlighted with recent developments with (instruction-based) language models, where users frequently have exchanges of messages with the models.

This workshop aims to bring together researchers from academia and industry working in XAI to explore limits of current explainability methods and discuss the view of explanations as an interactive process, and the interplay of natural language and explainability. The workshop will consist of invited and selected presentations and discussions.

Submission Guidelines

If you would like to give a short presentation around the workshop's topics, please submit a title and a short abstract by 10th of September, 23:59 GMT+1 (UK time).