RAPID DRL AI: Empowering Teachers to Collaborate with Generative AI for Developing High-Quality STEM Learning Resources

大型语言模型（LLM）的快速发展为大规模创建交互式个性化学习资源提供了巨大的机会。为了充分利用这些技术的教育潜力，至关重要的是，教师--他们处于学生日常互动的最前沿，拥有不可或缺的知识和专业知识--在这一过程中发挥关键作用。这个时间敏感的项目解决了对可行机制的迫切需求，使教师能够在通过视频学习的背景下，通过教师-人工智能协作范式利用LLM的能力。该研究团队将与波士顿PBS电视台WGBH教育基金会（GBH）合作，支持教师创建和定制智能导师，并在PBS LearningMedia上提供STEM学习资源，PBS LearningMedia是一个已经在全国教师中流行的平台，拥有超过5，000个高质量STEM视频和数百万用户的综合图书馆。本提案是对亲爱的同事信（DCL）的回应：在正式和非正式环境中快速加速人工智能在K-12教育中的研究（NSF 23-097），并由学生和教师创新技术经验（ITEST）计划资助，该计划支持建立对实践，计划要素，有助于增加学生对科学，技术，工程，信息和通信技术（ICT）智能导师将被纳入视频，并向学生提出理解问题，并在观看视频期间提供个性化反馈。该团队将迭代设计和开发一个教师-人工智能协作平台，允许教师监督智能导师生成问题序列和反馈。该平台将为教师提供“LLM积木”，以指导LLM产生理想的输出。因此，教师可以控制导师与学生的教学对话，确保此类对话符合教师的教学目标和学生的独特需求。然后，该团队将生成证据，证明拟议机制的可行性和潜在有效性，以及使非技术领域专家能够显著参与基于人工智能的教育资源开发的具体设计策略。该项目有可能产生更广泛的影响，因为它建立在现有的PBS学习媒体平台上。这确保了拟议平台的可持续性，并覆盖了大量教育工作者。通过公开平台，这项研究将使教育工作者能够继续制作满足其特定教育需求的互动视频。该奖项体现了NSF的法定使命，通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

The rapid advances in large language models (LLMs) have presented tremendous opportunities to create interactive, personalized learning resources on a large scale. To fully harness the educational potential of these technologies, it is crucial that teachers - who are at the forefront of daily student interaction and possess indispensable knowledge and expertise - serve as key contributors in the process. This time-sensitive project addresses the urgent need for viable mechanisms to empower teachers to harness the capabilities of LLMs through a teacher-AI collaboration paradigm in the context of learning through video. The research team will partner with WGBH Educational Foundation (GBH), Boston’s PBS station, to support teachers in creating and customizing an intelligent tutor that accompanies the STEM learning resources available on PBS LearningMedia, a platform already popular among teachers nationwide, with a comprehensive library of over 5,000 high quality STEM-focused videos and millions of users. This proposal was received in response to the Dear Colleague Letter (DCL): Rapidly Accelerating Research on Artificial Intelligence in K-12 Education in Formal and Informal Settings (NSF 23-097) and funded by the Innovative Technology Experiences for Students and Teachers (ITEST) program, which supports projects that build understandings of practices, program elements, contexts and processes contributing to increasing students' knowledge and interest in science, technology, engineering, and mathematics (STEM) and information and communication technology (ICT) careers.Intelligent tutors will be incorporated into videos and pose comprehension questions to students and provide personalized feedback during video viewing. The team will iteratively design and develop a teacher-AI collaborative platform that allows teachers to oversee the intelligent tutors’ generation of question sequences and feedback. The platform will provide "LLM building blocks" for teachers to steer LLMs to generate desirable outputs. Thus, teachers maintain control over the tutors' instructional dialogue with students, ensuring such dialogue aligns with teachers’ instructional objectives and the unique needs of their students. The team will then generate evidence demonstrating the feasibility and potential effectiveness of the proposed mechanism and specific design strategies that enable non-technical domain experts to have significant involvement in the development of AI-based educational resources. This project has the potential for a substantial broader impact, as it builds upon the existing PBS LearningMedia platform. This ensures the sustainability of the proposed platform and reach a large number of educators. By making the platform publicly available, this research will enable educators to continue generating interactive videos that cater to their specific educational needs. This work holds the promise of democratizing access to AI for teachers and promoting their active involvement in the production of AI-based learning resources.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.