Poster · Sydney
The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment
- 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
- Jiachen Zhao, Zhengxuan Wu, Aryaman Arora, Yiyou Sun, David Bau, Weiyan Shi
- Organisations
- Northeastern University, Google DeepMind, Stanford University, University of California, Berkeley
- QRS classification
- Language models