Poster · Sydney
From Facts to Personas: Interpretable Role Unlearning in LLMs via Mixture-of-Experts
- When
- Tue 8 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 1
- Authors
- Ruihong Zeng, Puning Yang, Jinghui Zhang, Shen Gao, Xiangliang Zhang, Preslav Nakov, Xiuying Chen
- Organisations
- Mohamed bin Zayed University of Artificial Intelligence, University of Electronic Science and Technology of China, University of Notre Dame
- QRS classification
- Language models, Safety, fairness and privacy