Login / Signup
Aligning a medium-size GPT model in English to a small closed domain in Spanish using reinforcement learning.
Oscar R. Navarrete-Parra
Victor Uc-Cetina
Jorge Reyes-Magaña
Published in:
CoRR (2023)
Keyphrases
</>
medium size
formal model
reinforcement learning
mathematical model
parameter estimation
computational model
machine learning
management system
state space
high level
domain specific
cost function
artificial neural networks
statistical model
experimental data
machine translation
domain models
learning algorithm