@inproceedings{zhang-yang-2025-finmoe,
title = "{F}in{M}o{E}: A {M}o{E}-based Large {C}hinese Financial Language Model",
author = "Zhang, Xuanyu and
Yang, Qing",
editor = "Chen, Chung-Chi and
Moreno-Sandoval, Antonio and
Huang, Jimin and
Xie, Qianqian and
Ananiadou, Sophia and
Chen, Hsin-Hsi",
booktitle = "Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.finnlp-1.4/",
pages = "48--53",
abstract = "Large-scale language models have demonstrated remarkable success, achieving strong performance across a variety of general tasks. However, when applied to domain-specific fields, such as finance, these models face challenges due to the need for both specialized knowledge and robust general capabilities. In this paper, we introduce FinMoE, a MOE-based large-scale Chinese financial language model that bridges the gap between general language models and domain-specific requirements. FinMoE employs a dense MoE architecture, where all expert networks are simultaneously activated and dynamically combined to effectively integrate general linguistic understanding with domain-specific financial expertise. Experimental results demonstrate that FinMoE achieves state-of-the-art performance on both general-purpose and financial benchmarks at a comparable scale, validating its ability to balance domain specialization with general knowledge and reasoning."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-yang-2025-finmoe">
<titleInfo>
<title>FinMoE: A MoE-based Large Chinese Financial Language Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuanyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qing</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Moreno-Sandoval</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jimin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianqian</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large-scale language models have demonstrated remarkable success, achieving strong performance across a variety of general tasks. However, when applied to domain-specific fields, such as finance, these models face challenges due to the need for both specialized knowledge and robust general capabilities. In this paper, we introduce FinMoE, a MOE-based large-scale Chinese financial language model that bridges the gap between general language models and domain-specific requirements. FinMoE employs a dense MoE architecture, where all expert networks are simultaneously activated and dynamically combined to effectively integrate general linguistic understanding with domain-specific financial expertise. Experimental results demonstrate that FinMoE achieves state-of-the-art performance on both general-purpose and financial benchmarks at a comparable scale, validating its ability to balance domain specialization with general knowledge and reasoning.</abstract>
<identifier type="citekey">zhang-yang-2025-finmoe</identifier>
<location>
<url>https://aclanthology.org/2025.finnlp-1.4/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>48</start>
<end>53</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FinMoE: A MoE-based Large Chinese Financial Language Model
%A Zhang, Xuanyu
%A Yang, Qing
%Y Chen, Chung-Chi
%Y Moreno-Sandoval, Antonio
%Y Huang, Jimin
%Y Xie, Qianqian
%Y Ananiadou, Sophia
%Y Chen, Hsin-Hsi
%S Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal)
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F zhang-yang-2025-finmoe
%X Large-scale language models have demonstrated remarkable success, achieving strong performance across a variety of general tasks. However, when applied to domain-specific fields, such as finance, these models face challenges due to the need for both specialized knowledge and robust general capabilities. In this paper, we introduce FinMoE, a MOE-based large-scale Chinese financial language model that bridges the gap between general language models and domain-specific requirements. FinMoE employs a dense MoE architecture, where all expert networks are simultaneously activated and dynamically combined to effectively integrate general linguistic understanding with domain-specific financial expertise. Experimental results demonstrate that FinMoE achieves state-of-the-art performance on both general-purpose and financial benchmarks at a comparable scale, validating its ability to balance domain specialization with general knowledge and reasoning.
%U https://aclanthology.org/2025.finnlp-1.4/
%P 48-53
Markdown (Informal)
[FinMoE: A MoE-based Large Chinese Financial Language Model](https://aclanthology.org/2025.finnlp-1.4/) (Zhang & Yang, FinNLP 2025)
ACL
- Xuanyu Zhang and Qing Yang. 2025. FinMoE: A MoE-based Large Chinese Financial Language Model. In Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal), pages 48–53, Abu Dhabi, UAE. Association for Computational Linguistics.