Poster · Sydney
AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens
- When
- Thu 10 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 5
- Authors
- Tung-Ling Li, Yuhao Wu, Hongliang Liu
- Organisations
- Crusoe.ai, Palo Alto Networks
- QRS classification
- Language models, Safety, fairness and privacy