FAST: Improving Controllability for Text Generation with Feedback Aware Self-Training Paper • 2210.03167 • Published Oct 6, 2022
Semi-Offline Reinforcement Learning for Optimized Text Generation Paper • 2306.09712 • Published Jun 16, 2023
Aligning the Query Space: Greedy Information Projection for Language Model Data Selection Paper • 2603.13790 • Published 26 days ago • 1
Aligning the Query Space: Greedy Information Projection for Language Model Data Selection Paper • 2603.13790 • Published 26 days ago • 1