Attribution: Tracing Influence to Inputs and Model Components | Gabriele Sarti

Attribution: Tracing Influence to Inputs and Model Components

Gabriele Sarti
Natural Language Processing, Academic
Project Project Slides

Date
Feb 24, 2026
Event
Invited Lecture, CS7810 - Neural Mechanics, Northeastern University
Location
Hayden Hall 321, Northeastern University
Boston, MA, USA
Natural Language Processing Interpretability Language Modeling Feature Attribution Retrieval-augmented Generation Mechanistic Interpretability

Related