New article presented at Mensch und Computer Conference and published in the Proceedings

(06.09.2023) At the largest European human-computer-interaction conference, Florian Leiser presented our paper “From ChatGPT to FactGPT: A Participatory Design Study to Mitigate the Effects of Large Language Model Hallucinations on Users” in Rapperswil, Switzerland.

In the study, he and his co-workers Sven Eckhardt, Merlin Knaeble, Alexander Maedche, Gerhard Schwabe, and Ali Sunyaev investigated how users want to be informed about potentially incorrect information in the responses of large language models. If you want to find out what their participants told them, have a look at the published paper at: