51±¾É«

The field of research known as Explainable Artificial Intelligence (XAI) is already developing approaches to automatically generate explanations for decisions made by artificial intelligence (AI). In order to design and deploy explanations effectively, it is essential to understand how explanations affect users’ interactions with AI. In the German-Israeli project "Guess The City / explAIn – lehAsbIr", we are investigating the role that explanations from modern XAI methods can play in the context of AI-supported learning – "Lehasbir" means "to explain" in Hebrew.

The question of how XAI can support users in their learning has so far received little scientific attention. In practice, too, XAI is not yet frequently implemented in learning contexts, despite its great potential. As part of the project, we are therefore developing a learning app that generates explanations for its users based on the current state of XAI research and are investigating its effectiveness. Users are presented with an educational game in which they match images from Google Street View of four cities in Germany and Israel – Berlin, Hamburg, Tel Aviv and Jerusalem – to the respective city. The AI attempts the same task. Users are shown how the AI arrived at its decision by highlighting the image elements essential for the assignment (marking of ‘feature relevance’). The app is implemented with a user-friendly interface and is easily accessible to users either via smartphone or via a web browser on a computer. At the end, users receive a score for their answers, allowing them to compare their performance with that of the AI.

Cooperation partner: Prof. Dr Lior Fink from the Behavioural Information Technology (BIT) Lab at Ben Gurion University in Beer Sheva, Israel

Project period: September 2021 – September 2022