Confidence-Reward Driven Preference Optimization for Machine Translation
from Neural intel Pod Hosted by Neuralintel.org
The paper "CRPO: Confidence-Reward Driven Preference Optimization for Machine Translation" introduces a novel approach to improving machine translation (MT) performance by leveraging both reward scores and model confidence for data selection during fine-tuning.
Embed this episode
No transcript yet.
Frequently asked questions
How long is this episode of Neural intel Pod?
This episode is 20 minutes long.
When was this Neural intel Pod episode published?
This episode was published on February 9, 2025.
Can I download this Neural intel Pod episode?
Yes. Use the download control on the episode player to save the publisher-provided media file.