Interpretability for Language Models: Trends and Applications | Gabriele Sarti

Interpretability for Language Models: Trends and Applications

Gabriele Sarti

Natural Language Processing, Academic

Code Project Project Slides

Date

Dec 18, 2025

Event

DEI Seminar

Location

Università di Padova, Italy

Padova, Veneto, Italy

Natural Language Processing Interpretability Sequence-to-sequence Language Modeling Feature Attribution Retrieval-augmented Generation Concept-based Interpretability Sparse Autoencoders