Saved in:
Bibliographic Details
Main Authors: Zhu, Jie, Chen, Qian, Dou, Huaixia, Li, Junhui, Guo, Lifan, Chen, Feng, Zhang, Chi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.15716
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912340722581504
author Zhu, Jie
Chen, Qian
Dou, Huaixia
Li, Junhui
Guo, Lifan
Chen, Feng
Zhang, Chi
author_facet Zhu, Jie
Chen, Qian
Dou, Huaixia
Li, Junhui
Guo, Lifan
Chen, Feng
Zhang, Chi
contents Effective reasoning remains a core challenge for large language models (LLMs) in the financial domain, where tasks often require domain-specific knowledge, precise numerical calculations, and strict adherence to compliance rules. We propose DianJin-R1, a reasoning-enhanced framework designed to address these challenges through reasoning-augmented supervision and reinforcement learning. Central to our approach is DianJin-R1-Data, a high-quality dataset constructed from CFLUE, FinQA, and a proprietary compliance corpus (Chinese Compliance Check, CCC), combining diverse financial reasoning scenarios with verified annotations. Our models, DianJin-R1-7B and DianJin-R1-32B, are fine-tuned from Qwen2.5-7B-Instruct and Qwen2.5-32B-Instruct using a structured format that generates both reasoning steps and final answers. To further refine reasoning quality, we apply Group Relative Policy Optimization (GRPO), a reinforcement learning method that incorporates dual reward signals: one encouraging structured outputs and another rewarding answer correctness. We evaluate our models on five benchmarks: three financial datasets (CFLUE, FinQA, and CCC) and two general reasoning benchmarks (MATH-500 and GPQA-Diamond). Experimental results show that DianJin-R1 models consistently outperform their non-reasoning counterparts, especially on complex financial tasks. Moreover, on the real-world CCC dataset, our single-call reasoning models match or even surpass the performance of multi-agent systems that require significantly more computational cost. These findings demonstrate the effectiveness of DianJin-R1 in enhancing financial reasoning through structured supervision and reward-aligned learning, offering a scalable and practical solution for real-world applications.
format Preprint
id arxiv_https___arxiv_org_abs_2504_15716
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DianJin-R1: Evaluating and Enhancing Financial Reasoning in Large Language Models
Zhu, Jie
Chen, Qian
Dou, Huaixia
Li, Junhui
Guo, Lifan
Chen, Feng
Zhang, Chi
Artificial Intelligence
Effective reasoning remains a core challenge for large language models (LLMs) in the financial domain, where tasks often require domain-specific knowledge, precise numerical calculations, and strict adherence to compliance rules. We propose DianJin-R1, a reasoning-enhanced framework designed to address these challenges through reasoning-augmented supervision and reinforcement learning. Central to our approach is DianJin-R1-Data, a high-quality dataset constructed from CFLUE, FinQA, and a proprietary compliance corpus (Chinese Compliance Check, CCC), combining diverse financial reasoning scenarios with verified annotations. Our models, DianJin-R1-7B and DianJin-R1-32B, are fine-tuned from Qwen2.5-7B-Instruct and Qwen2.5-32B-Instruct using a structured format that generates both reasoning steps and final answers. To further refine reasoning quality, we apply Group Relative Policy Optimization (GRPO), a reinforcement learning method that incorporates dual reward signals: one encouraging structured outputs and another rewarding answer correctness. We evaluate our models on five benchmarks: three financial datasets (CFLUE, FinQA, and CCC) and two general reasoning benchmarks (MATH-500 and GPQA-Diamond). Experimental results show that DianJin-R1 models consistently outperform their non-reasoning counterparts, especially on complex financial tasks. Moreover, on the real-world CCC dataset, our single-call reasoning models match or even surpass the performance of multi-agent systems that require significantly more computational cost. These findings demonstrate the effectiveness of DianJin-R1 in enhancing financial reasoning through structured supervision and reward-aligned learning, offering a scalable and practical solution for real-world applications.
title DianJin-R1: Evaluating and Enhancing Financial Reasoning in Large Language Models
topic Artificial Intelligence
url https://arxiv.org/abs/2504.15716