Defending LLMs against Jailbreak Attacks via Template-Based ICL with a Defensive Suffix.
Ruiyang Ni, Changlong Li, Shuaibiao Han, Zhiyu Yi, Perley Xu, Wenjie Ruan
Browse the full ACL paper archive.
Ruiyang Ni, Changlong Li, Shuaibiao Han, Zhiyu Yi, Perley Xu, Wenjie Ruan
Browse the full ACL paper archive.