生成式人工智能及其教育应用的基本争议和对策

Generative AI and its Uses in Education:Foundational Controversies and Responding Strategies

本文是对联合国教科文组织《生成式人工智能教育与研究应用指南》的系列解读第二篇,着重讨论生成式人工智能及其教育应用引发的基本争议。“基于工作过程”技术缺陷,生成式人工智能已引发加速数据贫穷、技术不透明导致服务辖区内治理缺失、未经许可搜集训练用数据、模型架构不可解释、基础模型不理解真实世界、生成的信息污染互联网、强势价值观投射、助长违法性深伪等多重争议。生成式人工智能会对平等、包容、学习主体能动性、价值观及语言文化多样性、知识建构的多元性等教育核心价值产生直接而深远的冲击,而这些核心价值应被秉承为考证生成式人工智能教育适用性的逻辑基点。决策者和实践者应遵循“优先管制、确保包容、引导应用”的逻辑路径,强化全系统监管法规和执法能力,确保教育生成式人工智能生态系统安全可信、自主可控、本地适用,进而通过能力建设和实践指导等措施引导合理的教育应用实践。

The paper is the second edition of a serials of interpretative articles on the Guidance on generative AI in education and research released by UNESCO,and the main aim of this edition is to examine the controversies around generative AI and its use in education.Based on an analysis of how it works,the development and deployment of generative AI have triggered the following controversies:worsening digital poverties,outpacing domestic governance,the collection of pre-training data without consent,the unexplainability of the architecture,the foundational models can't under the real world,the outputs of generative AI is polluting the internet,the outputs are projecting dominant values,amplifying the creation and dissemination of illegal deepfakes.Generative AI poses direct and most profound threats on the core values of education including inclusion,equity,cultural and linguistic diversities,pluralism in knowledge construction and expression,and therefore,those core values should be upheld as the logic base when examining the proportionality of generative AI to service purposes of education.Policy-makers and practitioners should follow the logic roadmap of"prioritizing regulation,ensuring inclusion,and guiding applications"to enhance the system-wide governance regulations in order to ensure trustable,self-automatic,and locally relevant eco-systems of generative AI for education,followed by developing capacities and guidance to steer proper uses of generative AI in education.