Poster · Sydney
MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment
- 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
- Junyoung Park, Namgyu Park, Sechan Lee, Yoon-Chan Jhi, Jihoon Cho, Sangdon Park
- Organisations
- POSTECH, Samsung
- QRS classification
- Reinforcement learning, Language models, Safety, fairness and privacy