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
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
Post-hoc Interpretability for Neural Language Models
Post-hoc Interpretability for Neural Language Models
Cite
×