SilverSight: A Multi-Task Chinese Financial Large Language Model Based on Adaptive Semantic Space Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Yuhang, Li, Zeping, Tian, Siyu, Ni, Yuchen, Liu, Sen, Ye, Guangnan, Chai, Hongfeng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911829792391168
author Zhou, Yuhang
Li, Zeping
Tian, Siyu
Ni, Yuchen
Liu, Sen
Ye, Guangnan
Chai, Hongfeng
author_facet Zhou, Yuhang
Li, Zeping
Tian, Siyu
Ni, Yuchen
Liu, Sen
Ye, Guangnan
Chai, Hongfeng
contents Large language models (LLMs) are increasingly being applied across various specialized fields, leveraging their extensive knowledge to empower a multitude of scenarios within these domains. However, each field encompasses a variety of specific tasks that require learning, and the diverse, heterogeneous data across these domains can lead to conflicts during model task transfer. In response to this challenge, our study introduces an Adaptive Semantic Space Learning (ASSL) framework, which utilizes the adaptive reorganization of data distributions within the semantic space to enhance the performance and selection efficacy of multi-expert models. Utilizing this framework, we trained a financial multi-task LLM named "SilverSight". Our research findings demonstrate that our framework can achieve results close to those obtained with full data training using only 10% of the data, while also exhibiting strong generalization capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2404_04949
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SilverSight: A Multi-Task Chinese Financial Large Language Model Based on Adaptive Semantic Space Learning
Zhou, Yuhang
Li, Zeping
Tian, Siyu
Ni, Yuchen
Liu, Sen
Ye, Guangnan
Chai, Hongfeng
Computation and Language
Computational Engineering, Finance, and Science
Large language models (LLMs) are increasingly being applied across various specialized fields, leveraging their extensive knowledge to empower a multitude of scenarios within these domains. However, each field encompasses a variety of specific tasks that require learning, and the diverse, heterogeneous data across these domains can lead to conflicts during model task transfer. In response to this challenge, our study introduces an Adaptive Semantic Space Learning (ASSL) framework, which utilizes the adaptive reorganization of data distributions within the semantic space to enhance the performance and selection efficacy of multi-expert models. Utilizing this framework, we trained a financial multi-task LLM named "SilverSight". Our research findings demonstrate that our framework can achieve results close to those obtained with full data training using only 10% of the data, while also exhibiting strong generalization capabilities.
title SilverSight: A Multi-Task Chinese Financial Large Language Model Based on Adaptive Semantic Space Learning
topic Computation and Language
Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2404.04949