大模型教育应用展望:基于技术预见的方法  

Prospects on the Applications of Large Language Models in Education:An Approach base on Technology Foresight

作　　者：陈向东[1] 靳旭莹 CHEN Xiang-dong;JIN Xu-ying(Department of Educational Technology and Information Science,East China Normal University,Shanghai 200062,China)

机构地区：[1]华东师范大学教育信息技术学系,上海200062

出　　处：《苏州大学学报(教育科学版)》2025年第1期13-24,共12页Journal of Soochow University(Educational Science Edition)

基　　金：全国教育科学规划一般课题“基于大语言模型的青少年人工智能教育研究”(项目编号:BCA230276)的阶段性研究成果。

摘　　要：作为一种公认的颠覆性技术,大模型在教育领域的应用亟须全面地审视,以评估可能出现的复杂场景及其后果。本研究从聚焦未来导向、鼓励广泛的多元参与、关注多重并发路径、承认不确定性、挖掘技术应用的深层因素等角度,分析技术预见对于探讨大模型教育应用的适用性,以中国人工智能学会的系列研究报告«大型语言模型的教育应用»为例,展示如何通过技术预见活动和相应的工具GPT-EDU4SIGHT,从大模型对教育不同方面的影响、典型应用场景、背后的心理机制、应用的伦理挑战以及基于大模型人工智能基础教育等五个维度进行大模型教育应用的前瞻性探索。技术预见在塑造未来教育中扮演重要的角色,为教育政策制定者、技术开发者和教育实践者提供了一种全新的思考和行动的框架。相应的技术工具也为大模型应用于教育决策和教育治理提供了示范案例。Recognized as a disruptive technology,large language models(LLMs)in the field of education require a comprehensive examination to evaluate complex scenarios and their consequences.From the perspectives of focusing on future orientation,encouraging widespread participation,paying attention to multiple concurrent paths,recognizing uncertainty,and exploring the deep factors of technologyapplication,analyzing the applicability of technology foresight in exploring the education application of LLMs.Taking the series of research reports of the Chinese Association for Artificial Intelligence,“Education Application of Large Language Models”as an example,it shows how technology foresight activities and corresponding tools like GPT-EDU4SIGHTcan prospectively explore the education application of LLMs from five dimensions:impact on different aspects of education,typical application scenarios,underlying psychological mechanisms,ethical challenges of application,and foundation education based on artificial intelligence.This article highlights the important role of technology foresight in shaping the future of education,which offers a new framework for educators,policymakers,and developers to think and act.The corresponding technical tools also provide demonstrative cases for the application of LLMs in education decision-making and governance.

关 键 词：大模型 技术预见 应用场景 GPT-EDU4SIGHT 

分 类 号：G434[文化科学—教育学]