Skip to content
NeurIPS 2026 planner

Poster · Atlanta

Measuring and Strengthening Behavioral Suppression in Language Models

When
Thu 10 Dec 2026, 16:30–19:30 EST
Where
Hall C1, Georgia World Congress Center
Session
Atlanta Poster Session 4
Authors
Luxi (Lucy) He, Pengcheng Jiang, Jifan Zhang, Jiawei Han, Danqi Chen
Organisations
Princeton University, University of Illinois Urbana-Champaign, University of Wisconsin-Madison
QRS classification
Reinforcement learning, Language models

Open in scheduleOfficial page