Skip to content
conftrace_

reward augmented

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

data relabeling (1) llms (1) reward augmentation (1) quality score (1) training stability (1) generative adversarial network (1) maximum likelihood estimation (1) maximum likelihood (1) adversarial training (1) text generation (1)

Papers

Reward-Augmented Data Enhances Direct Preference Alignment of LLMs ICML 2025 ARAML: A Stable Adversarial Training Framework for Text Generation EMNLP 2019