Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment.

Geyang Guo Ranchi Zhao Tianyi Tang Xin Zhao Ji-Rong Wen

Published in: ICLR (2024)

Keyphrases

fine grained
coarse grained
access control
tightly coupled
reinforcement learning
signal processing
massively parallel
database
search engine
information extraction
data lineage