Tomer Ashuach's picture

8 1

Tomer Ashuach

Tomertech

·

AI & ML interests

LLM Interpretability, Knowledge and Unlearning

Recent Activity

upvoted a paper 8 days ago

Multi-Domain Explainability of Preferences

authored a paper 11 days ago

REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space

upvoted a paper 11 days ago

REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space

View all activity

Organizations

None yet

Collections 1

Papers 1

arxiv:2406.09325

models 0

None public yet

datasets 0

None public yet