Full Text:
<5>
CLC number:
On-line Access: 2025-11-10
Received: 2025-06-18
Revision Accepted: 2025-09-29
Crosschecked: 0000-00-00
Cited: 0
Clicked: 9
Three trustworthiness challenges in large language model based financial systems: real-world examples and mitigation strategies
| |||||||||||||
Shurui XU1, Feng LUO2, Shuyan LI1, Mengzhen FAN3, Zhongtian SUN4. Three trustworthiness challenges in large language model based financial systems: real-world examples and mitigation strategies[J]. Frontiers of Information Technology & Electronic Engineering, 1998, -1(-1): .
@article{title="Three trustworthiness challenges in large language model based financial systems: real-world examples and mitigation strategies",
author="Shurui XU1, Feng LUO2, Shuyan LI1, Mengzhen FAN3, Zhongtian SUN4",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="-1",
number="-1",
pages="",
year="1998",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.2500421"
}
%0 Journal Article
%T Three trustworthiness challenges in large language model based financial systems: real-world examples and mitigation strategies
%A Shurui XU1
%A Feng LUO2
%A Shuyan LI1
%A Mengzhen FAN3
%A Zhongtian SUN4
%J Journal of Zhejiang University SCIENCE C
%V -1
%N -1
%P
%@ 2095-9184
%D 1998
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.2500421
TY - JOUR
T1 - Three trustworthiness challenges in large language model based financial systems: real-world examples and mitigation strategies
A1 - Shurui XU1
A1 - Feng LUO2
A1 - Shuyan LI1
A1 - Mengzhen FAN3
A1 - Zhongtian SUN4
J0 - Journal of Zhejiang University Science C
VL - -1
IS - -1
SP -
EP -
%@ 2095-9184
Y1 - 1998
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.2500421
Abstract: The integration of large language models (LLMs) into financial applications has demonstrated remarkable potential for enhancing decision-making processes, automating operations, and delivering personalized services. However, the high-stakes nature of financial systems demands a very high level of trustworthiness that current LLMs often fail to meet. This study identifies and examines three major trustworthiness challenges in LLM-based financial systems: (1) Jailbreak Prompts that exploit vulnerabilities in model alignment to produce harmful or noncompliant responses; (2) Hallucination, where models generate factually incorrect outputs that can mislead financial decision- making; and (3) Bias and Fairness concerns, where demographic or institutional bias embedded in LLMs may result in unfair treatment of individuals or regions. To make these risks concrete, we designed three finance-relevant probes and evaluated a set of mainstream LLMs spanning both proprietary and open-source families. Across models, we observed risky behavior in at least one scenario per probe.Based on these findings, we systematically summarized the existing mitigation strategies that aim to address these risks. We argued that resolving these issues is not only vital for ensuring the responsible use of artificial intelligence (AI) in the financial sector but also for enabling its safe and scalable deployment.
Open peer comments: Debate/Discuss/Question/Opinion
<1>