Poster · Paris

Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs

Name: Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs
Start: 2026-12-09T12:30:00+01:00
End: 2026-12-09T14:30:00+01:00
Location: Paris Poster Hall, Paris

When: Wed 9 Dec 2026, 12:30–14:30 CET
Where: Paris Poster Hall
Session: Paris Poster Session 1
Authors: Naman Deep Singh, Maximilian Mueller, Amit Peleg, Francesco Croce, Matthias Hein
Organisations: Exponential Security Labs, Universtity of Tübingen, University of Tübingen
QRS classification: Language models, Safety, fairness and privacy

Open in schedule Official page