Training a helpful and harmless assistant with reinforcement learning from human feedback
收藏DataCite Commons2026-01-07 更新2026-05-05 收录
下载链接：
https://service.tib.eu/ldmservice/dataset/88c98003-16a4-4943-8853-a198911da984
下载链接
链接失效反馈官方服务：
资源简介：
The authors propose a novel approach that incorporates parameter-efficient tuning to better optimize control tokens, thus benefitting controllable generation.
提供机构：
TIB
创建时间：
2024-12-02
