Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning
Zhaowei Liu, Xin Guo, Fangqi Lou, Lingfeng Zeng, Jinyi Niu, Zixuan Wang, Jiajie Xu, Weige Cai, Ziwei Yang, Xueqian Zhao, Chao Li, Sheng Xu, Dezhi Chen, Yun Chen, Zuo Bai, Liwen Zhang
2025-03-21
Summary
This paper introduces an AI language model called Fin-R1 that's specifically designed to understand and reason about financial topics.
What's the problem?
Regular AI language models aren't always great at handling the complex language and data involved in finance.
What's the solution?
The researchers created Fin-R1, which is trained on financial data and uses a technique called reinforcement learning to improve its reasoning skills.
Why it matters?
This work matters because it can lead to AI tools that are better at helping people make financial decisions.
Abstract
Reasoning large language models are rapidly evolving across various domains. However, their capabilities in handling complex financial tasks still require in-depth exploration. In this paper, we introduce Fin-R1, a reasoning large language model specifically designed for the financial sector. Fin-R1 is built using a two-stage architecture, leveraging a financial reasoning dataset distilled and processed based on DeepSeek-R1. Through supervised fine-tuning (SFT) and reinforcement learning (RL) training, it demonstrates performance close to DeepSeek-R1 with a parameter size of 7 billion across a range of financial reasoning tasks. It achieves the state-of-the-art (SOTA) in the FinQA and ConvFinQA tasks between those LLMs in our evaluation, surpassing larger models in other tasks as well. Fin-R1 showcases strong reasoning and decision-making capabilities, providing solutions to various problems encountered in the financial domain. Our code is available at https://github.com/SUFE-AIFLM-Lab/Fin-R1.