Educational technology innovations that have been developed based on large language models (LLMs) have shown the potential to automate the laborious process of generating and analysing textual content. While various innovations have been developed to automate a range of educational tasks (e.g., question generation, feedback provision, and essay grading), there are concerns regarding the practicality and ethicality of these innovations. Such concerns may hinder future research and the adoption of LLMs-based innovations in authentic educational contexts. To address this, we conducted a systematic literature review of 118 peer-reviewed papers published since 2017 to pinpoint the current state of research on using LLMs to automate and support educational tasks. The practical and ethical challenges of LLMs-based innovations were also identified by assessing their technological readiness, model performance, replicability, system transparency, privacy, equality, and beneficence. The findings were summarised into three recommendations for future studies, including updating existing innovations with state-of-the-art models (e.g., GPT-3), embracing the initiative of open-sourcing models/systems, and adopting a human-centred approach throughout the developmental process. These recommendations could support future research to develop practical and ethical innovations for supporting diverse educational tasks and benefiting students, teachers, and institutions.
翻译：基于大型语言模型（LLMs）开发的教育技术创新显示出自动生成和分析文本内容的潜力。虽然已经开发出各种创新来自动化多种教育任务（例如问题生成、反馈提供和论文评分），但存在对这些创新的实际性和道德性的担忧。这些担忧可能会阻碍未来研究和 LLMs 基础创新在真实教育环境中的应用。为了解决这一问题，我们对 2017 年以来发表的 118 篇同行评议论文进行了系统性文献综述，以指出使用 LLMs 自动化和支持教育任务的研究现状。通过评估技术准备度、模型性能、可复制性、系统透明度、隐私、平等和善意，还识别了基于 LLMs 创新的实际和伦理挑战。将发现总结为三项建议，包括使用最先进的模型（例如 GPT-3）更新现有的创新、接受开源模型/系统的倡议，并在整个开发过程中采用以人为中心的方法。这些建议可以支持未来研究开发实际和道德的创新，以支持各种教育任务并使学生、教师和机构受益。
相关内容
微信扫码咨询专知VIP会员