ExTraSafe26: 1st Workshop on Explainability, Transparency, and Safety

ExTraSafe26 is the first workshop on explainability, transparency, and safety held as part of the 49th German Conference on Artificial Intelligence (KI2026). The workshop facilitates transdisciplinary discussion between AI research, human–AI interaction, practitioners, and law focusing on trustworthiness in AI systems and EU guidelines including the EU AI Act. It accepts research paper submissions and discussion entries for presentation at the workshop. The event takes place in Bremen, Germany on the dates indicated.

Opportunity to present work at the workshop; accepts research paper and discussion entry submissions.

Submissions are invited from researchers, practitioners and others; accepts research papers (up to 8 pages + references in Springer LNCS layout) and discussion entries (up to 5000 characters).

Submit a research paper (up to 8 pages + references in Springer LNCS layout) or a discussion entry (up to 5000 characters) according to the call for papers.