Program

09:00 - 09:45 Arrival & Registration

09.45 - 10:00 Eric Raidl (University of Tübingen)

                             Introduction: AI, Trust & Explainability.

10:00 - 11:00 Miriam Klopotek (University of Stuttgart)

                             En route towards physics-explainable ML with physics of complex systems 

11:10 - 11:50 Sara Blanco (University of Tübingen)

                             Human Trust in AI: a Relationship Beyond Reliance. 

11:50 - 12:30 Andrew Kirton (University of Leeds)

                             Commentary: The Meaning Behind 'Trusting AI'.

12:30 - 13:30 Lunch

13:30 - 14:10 Saeedeh Babaii (University of Tübingen)

                             GAN; A Promising Approach to Trustworthiness of AI.

14:10 - 15:20 David Danks (UC San Diego)

                              When Explanations Undermine Trust (online talk).

15:20 - 15:45 Coffee Break

15:45 - 16:45 Roundtable on Guidelines for Trustworthy AI.

18:30 Dinner at Mauganeschtle.

09.30 - 10:30 Sabine Roeser (TU Delft)

                             AI, Trust and Other Moral Emotions.

10:45 - 11:45 Juan Durán (TU Delft)

                             Computational Reliabilism and the Chances for an Epistemology of ML 

11:45 - 13:00 Lunch

13:00 - 13:40 Oliver Buchholz (University of Tübingen)

                             Means-End Epistemology for XAI.

13:40 - 14:20 Florian Boge (TU Dortmund)

                             Commentary: Understanding (and) Black Box Explanation Problems in Science.

14:30 - 15:10 Thomas Grote (University of Tübingen)

                             ML in Healthcare and the Methodological Priority of Epistemology over Ethics.

15:10 - 15:30 Coffee Break

15:30 - 16:30 Roundtable on guidelines for Explainable AI.

18:30 Dinner at Forelle.

09.15 - 09:55 Konstantin Genin (University of Tübingen)

                             Why not reliability?

10:00 - 11:00 Zeynep Akata / Stephan Alaniz (University of Tübingen)

                             Explainability in the Era of Large Language Models.

11:15 - 11:55 Timo Freisleben (University of Tübingen)

                             Dear XAI Community, We Need to Talk! Fundamental Misconceptions in Current XAI Research. 

12:00 - 13:00 Lunch

13:00 - 13:40 Sebastian Bordt (University of Tübingen)

                             Explanations and Regulation.

13:45 - 14:45 Wulf Loh (University of Tübingen)

                             Can You Feel My Pain Tonight? Trust and Epistemic Injustice in AI-assisted Pain Detection.

14:45 - 15:15 Closing Roundtable (on both Guidelines for Trustworthy and Explainable AI).

16:00 - 17:00 Boat tour (Stocherkahnfahrt).

17:30 - 19:00 Guided tour through town.

            19:30 Dinner at 1821.