Poster · Atlanta

RA²: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning

Name: RA²: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning
Start: 2026-12-09T16:30:00-05:00
End: 2026-12-09T19:30:00-05:00
Location: Hall C1, Georgia World Congress Center

When: Wed 9 Dec 2026, 16:30–19:30 EST
Where: Hall C1, Georgia World Congress Center
Session: Atlanta Poster Session 2
Authors: Zinan Ling, Yang Xiao, Ruimeng Ye, Sijia Liu, Bo Hui
Organisations: University of Tulsa, Michigan State University, MIT-IBM Watson AI Lab
QRS classification: Language models, Safety, fairness and privacy

Open in schedule Official page