Poster · Sydney
On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation
- When
- Wed 9 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 3
- Authors
- Andy Q Han, Kristina Fujimoto, Avidan Shah, Kiet Nguyen, Kai Xu, Yueh-Han Chen, Ilia Sucholutsky, Rico Angell
- Organisations
- New York University, Purdue University
- QRS classification
- Language models, Safety, fairness and privacy