Poster · Sydney
Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing
- When
- Wed 9 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 4
- Authors
- Maryam Hashemzadeh Barvarz, Jerry Huang, Minseon Kim, Marc-Alexandre Côté, Sarath Chandar
- Organisations
- Université de Montréal, Mila, Microsoft, École Polytechnique
- QRS classification
- Language models, Safety, fairness and privacy