Skip to content
NeurIPS 2026 planner

Poster · Sydney

Self-Recognition Finetuning can Reverse and Prevent Emergent Misalignment

When
Thu 10 Dec 2026, 17:00–20:00 AEDT
Where
Hall 1-4, ICC Sydney
Exhibition Centre, Level 1
Session
Sydney Poster Session 6
Authors
Arush Tagade, Shaoheng Zhou, Jiaxin Wen, Shi Feng
Organisations
George Washington University, Google, University of California, Berkeley
QRS classification
Language models

Open in scheduleOfficial page