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.
@article{arxiv.2404.04949,
title = {SilverSight: A Multi-Task Chinese Financial Large Language Model Based on Adaptive Semantic Space Learning},
author = {Yuhang Zhou and Zeping Li and Siyu Tian and Yuchen Ni and Sen Liu and Guangnan Ye and Hongfeng Chai},
journal= {arXiv preprint arXiv:2404.04949},
year = {2024}
}