OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yuxiang, Yang, Yuqi, Shu, Jiangming, Wang, Yuhang, Xiao, Jinlin, Sang, Jitao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913622839525376
author Zhang, Yuxiang
Yang, Yuqi
Shu, Jiangming
Wang, Yuhang
Xiao, Jinlin
Sang, Jitao
author_facet Zhang, Yuxiang
Yang, Yuqi
Shu, Jiangming
Wang, Yuhang
Xiao, Jinlin
Sang, Jitao
contents OpenAI's recent introduction of Reinforcement Fine-Tuning (RFT) showcases the potential of reasoning foundation model and offers a new paradigm for fine-tuning beyond simple pattern imitation. This technical report presents \emph{OpenRFT}, our attempt to fine-tune generalist reasoning models for domain-specific tasks under the same settings as RFT. OpenRFT addresses two key challenges of lacking reasoning step data and the limited quantity of training samples, by leveraging the domain-specific samples in three ways: question augmentation, synthesizing reasoning-process data, and few-shot ICL. The evaluation is conducted on SciKnowEval, where OpenRFT achieves notable performance gains with only $100$ domain-specific samples for each task. More experimental results will be updated continuously in later versions. Source codes, datasets, and models are disclosed at: https://github.com/ADaM-BJTU/OpenRFT
format Preprint
id arxiv_https___arxiv_org_abs_2412_16849
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning
Zhang, Yuxiang
Yang, Yuqi
Shu, Jiangming
Wang, Yuhang
Xiao, Jinlin
Sang, Jitao
Artificial Intelligence
OpenAI's recent introduction of Reinforcement Fine-Tuning (RFT) showcases the potential of reasoning foundation model and offers a new paradigm for fine-tuning beyond simple pattern imitation. This technical report presents \emph{OpenRFT}, our attempt to fine-tune generalist reasoning models for domain-specific tasks under the same settings as RFT. OpenRFT addresses two key challenges of lacking reasoning step data and the limited quantity of training samples, by leveraging the domain-specific samples in three ways: question augmentation, synthesizing reasoning-process data, and few-shot ICL. The evaluation is conducted on SciKnowEval, where OpenRFT achieves notable performance gains with only $100$ domain-specific samples for each task. More experimental results will be updated continuously in later versions. Source codes, datasets, and models are disclosed at: https://github.com/ADaM-BJTU/OpenRFT
title OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning
topic Artificial Intelligence
url https://arxiv.org/abs/2412.16849