Research on knowledge-augmented Chinese financial large language model

The financial industry has long faced challenges in processing vast amounts of market data and information. Currently, large language models have made significant progress in general text understanding tasks, but there is still considerable room for improvement in more specialized domains, such as C...

Full description

Saved in:
Bibliographic Details
Main Authors: CHENG Dawei, JIA Renjun, LI Jiangtong, DING Zhijun, JIANG Changjun
Format: Article
Language:zho
Published: China InfoCom Media Group 2025-03-01
Series:大数据
Subjects:
Online Access:http://www.j-bigdataresearch.com.cn/thesisDetails#10.11959/j.issn.2096-0271.2025021
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849731667477921792
author CHENG Dawei
JIA Renjun
LI Jiangtong
DING Zhijun
JIANG Changjun
author_facet CHENG Dawei
JIA Renjun
LI Jiangtong
DING Zhijun
JIANG Changjun
author_sort CHENG Dawei
collection DOAJ
description The financial industry has long faced challenges in processing vast amounts of market data and information. Currently, large language models have made significant progress in general text understanding tasks, but there is still considerable room for improvement in more specialized domains, such as Chinese finance. To address the limitations of current large language models in handling professional domain-specific text tasks, a two-stage training approach based on finance knowledge-enhanced continued pre-training and supervised fine-tuning is designed. This approach improves the organization of training data and the training paradigm, thereby enhancing the model's capabilities in complex financial scenarios. Finally, experiments have validated the effectiveness of the proposed knowledge-enhanced approach in large model training.
format Article
id doaj-art-b61fa4b6170546f4adef07286c49c977
institution DOAJ
issn 2096-0271
language zho
publishDate 2025-03-01
publisher China InfoCom Media Group
record_format Article
series 大数据
spelling doaj-art-b61fa4b6170546f4adef07286c49c9772025-08-20T03:08:28ZzhoChina InfoCom Media Group大数据2096-02712025-03-011151886967683Research on knowledge-augmented Chinese financial large language modelCHENG DaweiJIA RenjunLI JiangtongDING ZhijunJIANG ChangjunThe financial industry has long faced challenges in processing vast amounts of market data and information. Currently, large language models have made significant progress in general text understanding tasks, but there is still considerable room for improvement in more specialized domains, such as Chinese finance. To address the limitations of current large language models in handling professional domain-specific text tasks, a two-stage training approach based on finance knowledge-enhanced continued pre-training and supervised fine-tuning is designed. This approach improves the organization of training data and the training paradigm, thereby enhancing the model's capabilities in complex financial scenarios. Finally, experiments have validated the effectiveness of the proposed knowledge-enhanced approach in large model training.http://www.j-bigdataresearch.com.cn/thesisDetails#10.11959/j.issn.2096-0271.2025021large language modelfinancial time series forecasting
spellingShingle CHENG Dawei
JIA Renjun
LI Jiangtong
DING Zhijun
JIANG Changjun
Research on knowledge-augmented Chinese financial large language model
大数据
large language model
financial time series forecasting
title Research on knowledge-augmented Chinese financial large language model
title_full Research on knowledge-augmented Chinese financial large language model
title_fullStr Research on knowledge-augmented Chinese financial large language model
title_full_unstemmed Research on knowledge-augmented Chinese financial large language model
title_short Research on knowledge-augmented Chinese financial large language model
title_sort research on knowledge augmented chinese financial large language model
topic large language model
financial time series forecasting
url http://www.j-bigdataresearch.com.cn/thesisDetails#10.11959/j.issn.2096-0271.2025021
work_keys_str_mv AT chengdawei researchonknowledgeaugmentedchinesefinanciallargelanguagemodel
AT jiarenjun researchonknowledgeaugmentedchinesefinanciallargelanguagemodel
AT lijiangtong researchonknowledgeaugmentedchinesefinanciallargelanguagemodel
AT dingzhijun researchonknowledgeaugmentedchinesefinanciallargelanguagemodel
AT jiangchangjun researchonknowledgeaugmentedchinesefinanciallargelanguagemodel