Poster · Sydney
BarrierSteer: LLM Safety via Learning Barrier Steering
- When
- Tue 8 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 2
- Authors
- Thanh Q. Tran, Arun Verma, Kiwan Wong, Bryan Kian Hsiang Low, Daniela Rus, Wei Xiao
- Organisations
- National University of Singapore, Singapore-MIT Alliance for Research and Technology Centre, Massachusetts Institute of Technology, Nanyang Technological University
- QRS classification
- Language models, Safety, fairness and privacy