Post

Florian Eichin
@florian-eichin.com

𝗚𝗿𝗮𝗱𝗶𝗲𝗻𝘁 𝗱𝗲𝘀𝗰𝗲𝗻𝘁 𝗶𝘀 𝗮𝗹𝗹 𝘆𝗼𝘂 𝗻𝗲𝗲𝗱 𝗳𝗼𝗿 𝗶𝗻𝘁𝗲𝗿𝗽𝗿𝗲𝘁𝗮𝗯𝗶𝗹𝗶𝘁𝘆? In our ICML paper, we show that it might just be. ExPLAIND is a method that unifies data attribution, model component attribution, and training dynamics by computing an exact decomposition of model behavior based on gradient products.

Florian Eichin
@florian-eichin.com

Want to learn more? Poster presentation at Tue, Jul 7, 2026, 2:00 PM – 3:45 PM @ HALL A #3303 Also in the workshop on mechanistic interpretability, Fri, Jul 10, 2026 • 8:00 AM – 5:00 PM @ HALL C Paper: arxiv.org/abs/2505.20076

arxiv.orgExPLAIND: Unifying Model, Data, and Training Attribution to Study Model BehaviorPost-hoc interpretability methods typically attribute a model's behavior to its components, data, or training trajectory in isolation, and are often tied to a particular level of granularity along the...

1 repost2 likes