Poster · Sydney
Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models
- When
- Tue 8 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 1
- Authors
- Haoxiang Wang, Da Yu, Huishuai Zhang
- Organisations
- Peking University, Google
- QRS classification
- Language models, Safety, fairness and privacy