基于风险感知偏好的安全可控文本生成
CCL
Lv, Rundong and Liu, Yuanxing and Zhang, Weinan and Liu, Ting
Rundong Lv
基于风险感知偏好的安全可控文本生成
CCL
Lv, Rundong and Liu, Yuanxing and Zhang, Weinan and Liu, Ting
Gradients with respect to semantics preserving embeddings tell the uncertainty of large language models
ICML
Mingda, Li and Rundong, Lv and Xinyu, Li and Weinan, Zhang and Ting, Liu
Gradients with respect to semantics preserving embeddings tell the uncertainty of large language models
ICML
Mingda, Li and Rundong, Lv and Xinyu, Li and Weinan, Zhang and Ting, Liu