SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs.
Zhengxian Wu, Juan Wen, Wanli Peng, Haowei Chang, Yinghan Zhou, Yiming Xue
Browse the full ACL paper archive.
Zhengxian Wu, Juan Wen, Wanli Peng, Haowei Chang, Yinghan Zhou, Yiming Xue
Browse the full ACL paper archive.