Second TRR 318 Conference: Measuring Understanding

Dates & Infos

The conference will take place on 6 and 7 November at Paderborn University.

Participation is free of registration fees. For those actively involved, we aim to cover some of the (travel) costs that arise.

Call for Abstracts

The TRR 318 is an interdisciplinary research centre on the topic of Constructing Explainability. According to the constructive view, if an explanation is successful, it results in an understanding. Current XAI research is centering around solutions of how to achieve understanding. This year’s topic of the 2. TRR conference is therefore “Measuring Understanding” and we call for contributions from diverse disciplines. The contributions can include different methods and tools to assess and measure understanding in the context of (a) dyadic everyday explanations (b) the context of interpretability or explainability of AI systems, or (c) of institutional environments. Specifically, the contributions should focus on the methodological challenge of how to measure and operationalise understanding in diverse explanatory settings including human-human interaction and human-machine interaction, and what are the implications of these measurements for XAI.

Format of submissions:

• extended abstract (1-2 pages including references)
• names, emails and affiliation
• title
• 4-5 keywords

Please submit your extended abstract (1-2 pages) as a .pdf and a .docx/.tex files to conference(at)trr318.uni-paderborn(dot)de until 15.05.2023. Notifications tba.

Formats of presentations:

Presentations might be given in a 20-minute oral presentation or as a poster. Please indicate your preferred format within the submission. The posters will already be printed and be handed out to you at the registration desk.
Note: If we are unable to include your oral presentation, we will automatically attempt to include it as a poster.

Call for Workshop Contributions

How to measure understanding in everyday explanations. Workshops shall give insights in how to assess understanding. This can include different types of questionnaires, video recalls, and many more. Therefore, detailed methodological procedures are of highest interest. Also, schemes for coding and scaling understanding are welcomed. The workshop contributions will be about 15 minutes long, and the abstract will be included in the conference proceedings.

Format of submissions:

• 300 words abstract
• names, emails, and affiliation
• title
• 4-5 keywords

Please submit your workshop abstract as .pdf and .docx/.tex file to conference(at)trr318.uni-paderborn(dot)de by 15.05.2023. Notifications tba.