Cite
Notes
Only stored in your browser.
Attribution
SoFA: Shielded On-the-fly Alignment via Priority Rule Following
arXiv 2024
Transferable Post-training via Inverse Value Learning
from 2 papers
Bowen Yu
Haiyang Yu
Hongyu Lin
Le Sun
Xianpei Han
Yaojie Lu
Yongbin Li
Xueru Wen