5 papers
SNAPE-PM: Building and Utilizing Dynamic Partner Models for Adaptive Explanation Generation
Amelie S. Robrecht, Christoph R. Kowalski, Stefan Kopp
Adapting to the addressee is crucial for successful explanations, yet poses significant challenges for dialogsystems. We adopt the approach of treating explanation generation as a…
Investigating Co-Constructive Behavior of Large Language Models in Explanation Dialogues
Leandra Fichtel, Maximilian Spliethöver, Eyke Hüllermeier +9
The ability to generate explanations that are understood by explainees is the quintessence of explainable artificial intelligence. Since understanding depends on the explainee's ba…
Measuring User Understanding in Dialogue-based XAI Systems
Dimitry Mindlin, Amelie Sophie Robrecht, Michael Morasch +1
The field of eXplainable Artificial Intelligence (XAI) is increasingly recognizing the need to personalize and/or interactively adapt the explanation to better reflect users' expla…
Towards an Analysis of Discourse and Interactional Pragmatic Reasoning Capabilities of Large Language Models
Amelie Robrecht, Judith Sieker, Clara Lachenmaier +2
In this work, we want to give an overview on which pragmatic abilities have been tested in LLMs so far and how these tests have been carried out. To do this, we first discuss the s…
Integrating Representational Gestures into Automatically Generated Embodied Explanations and its Effects on Understanding and Interaction Quality
Amelie Sophie Robrecht, Hendric Voss, Lisa Gottschalk +1
In human interaction, gestures serve various functions such as marking speech rhythm, highlighting key elements, and supplementing information. These gestures are also observed in…