Skip to content
conftrace_
2025 ICML ICML 2025

Towards Cost-Effective Reward Guided Text Generation

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Natural Language Processing and Reinforcement Learning

Authors

Ahmad Rashid, Ruotian Wu, Rongqi Fan, Hongliang Li, Agustinus Kristiadi, Pascal Poupart

Topics

Natural Language Processing > Generation > Text Generation Reinforcement Learning > Methods > Offline RL

Keywords

language model reward model bradley-terry loss candidate tokens generation process test-time overhead
Download PDF