Search Results for author:
Found 3 papers, 2 papers with code
ReFT: Reasoning with Reinforced Fine-Tuning
ReFT first warmups the model with SFT, and then employs on-line reinforcement learning, specifically the PPO algorithm in this paper, to further fine-tune the model, where an abundance of reasoning paths are automatically sampled given the question and the rewards are naturally derived from the ground-truth answers.
Design of Chain-of-Thought in Math Problem Solving
We also find that Python is a better choice of language than Wolfram for program CoTs.
Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understanding
This paper presents GenDoc, a general sequence-to-sequence document understanding model pre-trained with unified masking across three modalities: text, image, and layout.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
