Post-hoc Interpretability for Generative Language Models: Explaining Context Usage in Transformers | Gabriele Sarti
Home
About me
Publications
Blog
Talks
Projects
Activities
CV
Communities
AI2S
AISIG
Post-hoc Interpretability for Generative Language Models: Explaining Context Usage in Transformers
Gabriele Sarti
Natural Language Processing
,
Academic
Code
Project
Project
Slides
Date
Mar 1, 2024
Event
SheffieldNLP Invited Talk
Location
Online
Natural Language Processing
Interpretability
Sequence-to-sequence
Language Modeling
Feature Attribution
Related
Interpretability for Language Models: Current Trends and Applications
Interpreting Context Usage in Generative Language Models with Inseq and PECoRe
Post-hoc Interpretability for Language Models
Post-hoc Interpretability for NLG & Inseq: an Interpretability Toolkit for Sequence Generation Models
Explaining Neural Language Models from Internal Representations to Model Predictions
Cite
×