Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model

Haikang Deng, Colin Raffel

Main: Natural Language Generation Main-poster Paper

Poster_Demo_Industry_Findings In-person 6: Natural Language Generation (Poster)
Conference Room: East Foyer
Conference Time: December 10, 09:00-10:30 (+08) (Asia/Singapore)
Global Time: December 10, Poster_Demo_Industry_Findings In-person 6 (01:00-02:30 UTC)
TLDR:
You can open the #paper-4200 channel in a separate window.
Abstract: