Stanford's Chris Potts Keynotes Actionable Interpretability at COLM 2026

Stanford NLP's Chris Potts delivered a keynote on "Actionable Interpretability" at COLM 2026, arguing interpretability should shift from passive observation to causal intervention. The slides have been publicly released, with a video to follow.

2026-10-26 ~ 2026-10-26 · 2 related posts

• Chris Potts' COLM 2026 Actionable Interpretability keynote slides on SALVE now public — stanfordnlp · 2026-10-26
• Stanford NLP's COLM 2026 keynote: interpretability shifts from probing to causal steering — stanfordnlp · 2026-10-26