Cite
Notes
Only stored in your browser.
Attribution
Legend: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets
arXiv 2024
Empowering Many, Biasing a Few: Generalist Credit Scoring through Large Language Models
arXiv 2023
from 2 papers
Alejandro Lopez-Lira
Bowen Qin
Chen Huang
Hao Wang
Jimin Huang
Qianqian Xie
Weiguang Han
Wenqiang Lei
Yifang Zhang
Yongfu Dai