JZUS - Journal of Zhejiang University SCIENCE

Frontiers of Information Technology & Electronic Engineering

Accepted manuscript available online (unedited version)

When DeepSeek-R1 meets financial applications: benchmarking, opportunities, and limitations

Author(s): Shuoling LIU^1, ², Liyuan CHEN², Jiangpeng YAN^2, ⁴, Yuhang JIANG², Xiaoyu WANG², Xiu LI⁴, Qiang YANG¹
Affiliation(s): ¹The Hong Kong University of Science and Technology, Hong Kong 999077, China; more
Corresponding email(s): qyang@cse.ust.hk
Key Words: Large language models; Reasoning; Artificial intelligence; Financial technology; FinTech

Share this article to： More <<< Previous Paper \|Next Paper >>>

Shuoling LIU^1,², Liyuan CHEN², Jiangpeng YAN^2,⁴, Yuhang JIANG², Xiaoyu WANG², Xiu LI⁴, Qiang YANG¹. When DeepSeek-R1 meets financial applications: benchmarking, opportunities, and limitations[J]. Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/FITEE.2500227

@article{title="When DeepSeek-R1 meets financial applications: benchmarking, opportunities, and limitations",
author="Shuoling LIU^1,², Liyuan CHEN², Jiangpeng YAN^2,⁴, Yuhang JIANG², Xiaoyu WANG², Xiu LI⁴, Qiang YANG¹",
journal="Frontiers of Information Technology & Electronic Engineering",
year="in press",
publisher="Zhejiang University Press & Springer",
doi="https://doi.org/10.1631/FITEE.2500227"
}

%0 Journal Article
%T When DeepSeek-R1 meets financial applications: benchmarking, opportunities, and limitations
%A Shuoling LIU^1
%A²
%A Liyuan CHEN²
%A Jiangpeng YAN^2
%A⁴
%A Yuhang JIANG²
%A Xiaoyu WANG²
%A Xiu LI⁴
%A Qiang YANG¹
%J Frontiers of Information Technology & Electronic Engineering
%P
%@ 2095-9184
%D in press
%I Zhejiang University Press & Springer
doi="https://doi.org/10.1631/FITEE.2500227"

TY - JOUR
T1 - When DeepSeek-R1 meets financial applications: benchmarking, opportunities, and limitations
A1 - Shuoling LIU^{1
A1 -}²
A1 - Liyuan CHEN²
A1 - Jiangpeng YAN^{2
A1 -}⁴
A1 - Yuhang JIANG²
A1 - Xiaoyu WANG²
A1 - Xiu LI⁴
A1 - Qiang YANG¹
J0 - Frontiers of Information Technology & Electronic Engineering
SP -
EP -
%@ 2095-9184
Y1 - in press
PB - Zhejiang University Press & Springer
ER -
doi="https://doi.org/10.1631/FITEE.2500227"

Abstract
Chinese Summary
Academic Network
Reviewer Comment

Abstract: The ways in which the recent progresses of reasoning large language models (LLMs), especially the new open-source model DeepSeek-R1, can benefit financial services is an underexplored problem. While LLMs have ignited numerous applications within the financial sector, including financial news analysis and general customer interactions, DeepSeek-R1 further unlocks the advanced reasoning ability with multiple reinforcement learning–integrated training steps for more complex financial queries and provides distilled student models for resource-constrained scenarios. In this paper, we first introduce the technological preliminaries of DeepSeek-R1. Subsequently, we benchmark the performance of DeepSeek-R1 and its distilled students on two public financial question–answer datasets as a starting point for interdisciplinary research on financial artificial intelligence (AI). Then, we discuss the opportunities that DeepSeek-R1 offers to current financial services, its current limitations, and three future research directions. In conclusion, we argue for a proper approach to adopt reasoning LLMs for financial AI

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

Open peer comments: Debate/Discuss/Question/Opinion

<1>

- Go to

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference