金融大语言模型知识蒸馏：策略、应用与评估的系统综述

石家琪; 张旭龙; 瞿晓阳; 谢骏飞; 王健宗

doi:10.1631/FITEE.2500282

Your Location：

Home >

Browse articles >

金融大语言模型知识蒸馏：策略、应用与评估的系统综述

专题 | Updated：2025-11-18

- 金融大语言模型知识蒸馏：策略、应用与评估的系统综述
  Enhanced Publication
- Knowledge distillation for financial large language models: a systematic review of strategies, applications, and evaluation
- “在金融大语言模型领域，对知识提炼进行了全面的调查。xx专家建立了一个结构化的分类和综合评估框架，为解决部署支出和推理延迟问题提供了解决方案。”
- Frontiers of Information Technology & Electronic Engineering 2025年26卷第10期页码：1793-1808
- Affiliations：
  
  1.Ping An Technology (Shenzhen) Co., Ltd., Shenzhen 518046, China
  2.Institute of Advanced Technology, University of Science and Technology of China, Hefei 230027, China
- Author bio：
  
  E-mail: civilizwa@mail.ustc.edu.cn
  zhangxulong@ieee.org
  quxiaoy@gmail.com
  xiejunfei@mail.ustc.edu.cn
  ‡ Corresponding author
- Funds：
  
  National Key Research and Development Program of China (Youth Scientist Project)(2024YFB4504300)
- DOI：10.1631/FITEE.2500282
  中图分类号： TP391
- 收稿：2025-04-30，
  
  修回：2025-09-05，
  
  纸质出版：2025-10
- Accepted：
Scan QR Code
石家琪, 张旭龙, 瞿晓阳, 等. 金融大语言模型知识蒸馏：策略、应用与评估的系统综述[J]. Frontiers of Information Technology & Electronic Engineering, 2025,26(10):1793-1808.

Jiaqi SHI, Xulong ZHANG, Xiaoyang QU, et al. Knowledge distillation for financial large language models: a systematic review of strategies, applications, and evaluation[J]. Frontiers of Information Technology & Electronic Engineering, 2025, 26(10): 1793-1808.
石家琪, 张旭龙, 瞿晓阳, 等. 金融大语言模型知识蒸馏：策略、应用与评估的系统综述[J]. Frontiers of Information Technology & Electronic Engineering, 2025,26(10):1793-1808. DOI： 10.1631/FITEE.2500282.

Jiaqi SHI, Xulong ZHANG, Xiaoyang QU, et al. Knowledge distillation for financial large language models: a systematic review of strategies, applications, and evaluation[J]. Frontiers of Information Technology & Electronic Engineering, 2025, 26(10): 1793-1808. DOI： 10.1631/FITEE.2500282.

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Prototype-guided cross-task knowledge distillation

Quant 4.0: engineering quantitative investment with automated, explainable, and knowledge-driven artificial intelligence

Federated learning on non-IID and long-tailed data via dual-decoupling

Multi-exit self-distillation with appropriate teachers

Federated mutual learning: a collaborative machine learning method for heterogeneous data, models, and objectives

金融大语言模型知识蒸馏：策略、应用与评估的系统综述

Knowledge distillation for financial large language models: a systematic review of strategies, applications, and evaluation

DOI：10.1631/FITEE.2500282