TRR 318-2 - Project A02: Monitoring the understanding of explanations
Overview
Our goal is to build a computational architecture that will monitor a human interlocutor’s moments of (non)understanding in multimodal ensembles. We will make artificial EXs able to reason about these and adapt their explanatory strategy. Utilizing a large corpus of explanations (MUNDEX), we integrate rich, multimodal signals with different perspectives on EE’ level of understanding across varying contexts. Beyond modeling the monitoring and adaptation in explanations, we assess its usefulness for a dynamically adjustable social XAI.
Key Facts
- Project type:
- Forschung
- Project duration:
- 01/2026 - 06/2029
More Information
Publications
Syntactic complexity convergence in dialogue: Analysis of the phenomenon and application to LLM detection
Show all publications
Y. Wang, Y. Chen, Y. Wang, S. Eger, H. Buschmeier, in: Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, ACL, Budapest, Hungary, n.d.