Login / Signup
SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF.
Yi Dong
Zhilin Wang
Makesh Narsimhan Sreedhar
Xianchao Wu
Oleksii Kuchaiev
Published in:
EMNLP (Findings) (2023)
Keyphrases
</>
user interface
user interaction
recommender systems
relevance feedback
user requirements
user oriented
learning algorithm
human users
artificial intelligence
decision making
similarity measure
rough set theory
user groups
user authentication