Towards Test-Time Refusals via Concept Negation

Publication
In the 37th Annual Conference on Neural Information Processing Systems (NeurIPS) (CCF-A)
Peiran Dong
Peiran Dong
PhD Student
Song Guo
Song Guo
Chair Professor
Bingjie Wang
Bingjie Wang
PhD Student
Jiewei Zhang
Jiewei Zhang
PhD Student
Ziming Liu
Ziming Liu
Tencent