Tutor CoPilot:一种用于扩展实时专家知识的人机协作方法
Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertise
AI总结:
提出人机协作系统Tutor CoPilot,利用专家思维模型在实时辅导中为辅导教师提供指导,随机对照试验表明该方法能显著提高学生知识点掌握率,且成本低廉,有效促进了高质量教育公平。
摘要:
生成式人工智能,特别是语言模型(LMs),有望通过具有社会影响力的方式变革现实世界领域,尤其是在专家资源匮乏的环境中。例如,在教育领域,利用专家指导培训新手教育工作者对教学效果至关重要,但成本高昂,这构成了大规模提升教育质量的巨大障碍。这一挑战对服务不足社区的学生影响尤为严重,而这些学生恰恰是最能从高质量教育中获益的群体。我们提出了Tutor CoPilot,一种新颖的人机协作方法,它利用专家思维模型,在辅导过程中为辅导教师提供类专家的指导。本研究是首次在实时辅导中对人机系统进行的随机对照试验,共有来自历史上服务不足社区的900名辅导教师和1,800名K-12学生参与。根据预注册的分析计划,我们发现,在能够使用Tutor CoPilot的辅导教师指导下,学生掌握知识点的可能性提高了4个百分点(p.p.)(p<0.01)。值得注意的是,评分较低的辅导教师所教学生获益最大,掌握率提高了9个百分点。我们发现Tutor CoPilot的成本仅为每位辅导教师每年20美元。我们使用分类器分析了超过550,000条消息以识别教学策略,发现能够使用Tutor CoPilot的辅导教师更有可能使用高质量策略来促进学生的理解(例如,提出引导性问题),并且更少直接向学生透露答案。辅导教师访谈强调了Tutor CoPilot的指导如何帮助辅导教师响应学生需求,尽管他们也指出了Tutor CoPilot存在的一些问题,例如生成的建议不符合相应年级水平。总而言之,我们对Tutor CoPilot的研究展示了人机系统如何在现实世界的领域中扩展专家知识,弥合技能差距,并创造一个所有学生都能获得高质量教育的未来。
英文摘要:
Generative AI, particularly Language Models (LMs), has the potential to transform real-world domains with societal impact, particularly where access to experts is limited. For example, in education, training novice educators with expert guidance is important for effectiveness but expensive, creating significant barriers to improving education quality at scale. This challenge disproportionately harms students from under-served communities, who stand to gain the most from high-quality education. We introduce Tutor CoPilot, a novel Human-AI approach that leverages a model of expert thinking to provide expert-like guidance to tutors as they tutor. This study is the first randomized controlled trial of a Human-AI system in live tutoring, involving 900 tutors and 1,800 K-12 students from historically under-served communities. Following a preregistered analysis plan, we find that students working with tutors that have access to Tutor CoPilot are 4 percentage points (p.p.) more likely to master topics (p<0.01). Notably, students of lower-rated tutors experienced the greatest benefit, improving mastery by 9 p.p. We find that Tutor CoPilot costs only $20 per-tutor annually. We analyze 550,000+ messages using classifiers to identify pedagogical strategies, and find that tutors with access to Tutor CoPilot are more likely to use high-quality strategies to foster student understanding (e.g., asking guiding questions) and less likely to give away the answer to the student. Tutor interviews highlight how Tutor CoPilot's guidance helps tutors to respond to student needs, though they flag issues in Tutor CoPilot, such as generating suggestions that are not grade-level appropriate. Altogether, our study of Tutor CoPilot demonstrates how Human-AI systems can scale expertise in real-world domains, bridge gaps in skills and create a future where high-quality education is accessible to all students.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。