BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models
收藏DataCite Commons2025-01-03 更新2025-04-16 收录
下载链接：
https://service.tib.eu/ldmservice/dataset/c4e364bd-44be-40f8-a888-4b0236fae051
下载链接
链接失效反馈官方服务：
资源简介：
The dataset used in the paper to evaluate the effectiveness of the BEEAR method in mitigating safety backdoors in instruction-tuned LLMs.
提供机构：
TIB
创建时间：
2025-01-03
