Poster · Sydney
Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs
- 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
- Dylan Feng, Pragya Srivastava, Anca Dragan, Cassidy Laidlaw
- Organisations
- University of California, Berkeley, Google DeepMind, Transluce
- QRS classification
- Language models