Sign up to save your podcasts
Or
Share Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model
The paper introduces Reward-Augmented Decoding (RAD), a text generation procedure that uses a reward model to encourage a language model to generate text with desired properties. RAD outperforms other methods and has minimal computational overhead.
https://arxiv.org/abs//2310.09520
YouTube: https://www.youtube.com/@ArxivPapers
TikTok: https://www.tiktok.com/@arxiv_papers
Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016
Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers
View all episodes
By Igor Melnyk
5
33 ratings
The paper introduces Reward-Augmented Decoding (RAD), a text generation procedure that uses a reward model to encourage a language model to generate text with desired properties. RAD outperforms other methods and has minimal computational overhead.
https://arxiv.org/abs//2310.09520
YouTube: https://www.youtube.com/@ArxivPapers
TikTok: https://www.tiktok.com/@arxiv_papers
Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016
Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers
More shows like Arxiv Papers
View all
Exchanges
953 Listeners
Odd Lots
1,971 Listeners
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
438 Listeners
The Daily
112,759 Listeners
All-In with Chamath, Jason, Sacks & Friedberg
10,063 Listeners
Hard Fork
5,531 Listeners
UnHerd with Freddie Sayers
214 Listeners
Unsupervised Learning with Jacob Effron
51 Listeners
Latent Space: The AI Engineer Podcast
99 Listeners
BG2Pod with Brad Gerstner and Bill Gurley
473 Listeners