Preventing Safety Drift in Large Language Models via Coupled Weight and Activation Constraints.
Songping Peng, Zhiheng Zhang, Daojian Zeng, Lincheng Jiang, Xieping Gao
Browse the full ACL paper archive.
Songping Peng, Zhiheng Zhang, Daojian Zeng, Lincheng Jiang, Xieping Gao
Browse the full ACL paper archive.