Dagstuhl Seminar 27431
Mechanistic Interpretation of Generative AI Models
( Oct 24 – Oct 29, 2027 )
Permalink
Please use the following short url to reference this page:
https://www.dagstuhl.de/27431
Organizers
- James Allan (University of Massachusetts Amherst, US)
- Carsten Eickhoff (Universität Tübingen, DE)
- Kentaro Inui (MBZUAI - Abu Dhabi, AE)
- Ellie Pavlick (Brown University - Providence, US)
Contact
- Michael Gerke (for scientific matters)
- Jutka Gasiorowski (for administrative matters)
Classification
- Artificial Intelligence
- Computation and Language
- Information Retrieval
Keywords
- Mechanistic Interpretability
- Explainability
- Transparency
- Large Language Models
- Vision Language Models
