Poster · Sydney
Are LLM Safety Judges Policy-Invariant? A Three-Principle Stress-Test
- 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
- Shihao Weng, Yang Feng, Xiaofei Xie
- Organisations
- Nanjing University, Singapore Management University
- QRS classification
- Language models, Safety, fairness and privacy