The workshop on Actionable Interpretability@COLM2026 aims to foster discussions on leveraging interpretability insights to drive tangible advancements in AI across diverse domains. We welcome contributions that move beyond theoretical analysis, demonstrating concrete improvements in model alignment, robustness, and real-world applications. Additionally, we seek to explore the challenges inherent in translating interpretability research into actionable impact.
News
- June 15: Submission Deadline extended to June 24 + clarified double submission policy in the CFP
- May 22 2026: Call for Papers published
- May 13 2026: Our workshop was accepted to COLM!
Important Dates
June 21 24 - Submission Deadline (Submission Link)
October 9 - Workshop day
Dates are AOE.
Organizers
Tal Haklay
Member of technical staff, Goodfire
Hadas Orgad
Postdoc, Kempner Institute, Harvard University
Anja Reusch
Postdoc, Technion
Marius Mosbach
Postdoc, McGill University and Mila – Quebec AI Institute
Sarah Wiegreffe
Assistant Professor, University of Maryland
Ian Tenney
Staff Research Scientist, Google DeepMind
Mor Geva
Assistant Professor, Tel Aviv University