Kwame 2.0：面向非洲大规模在线编程教育的人机协同生成式AI助教
Kwame 2.0: Human-in-the-Loop Generative AI Teaching Assistant for Large Scale Online Coding Education in Africa
AI总结：
Kwame 2.0通过检索增强生成技术，在非洲35个国家的15个班级中为3717名学生提供及时准确的学习支持，结合人类监督和社区参与，有效提升编程课程的教学质量。
摘要：
在大规模在线编程课程中，提供及时准确的学习支持具有挑战性，尤其是在资源受限的环境中。我们介绍了Kwame 2.0，这是一个双语（英语-法语）的生成式AI助教，采用检索增强生成技术，并在SuaCode的入门移动编程课程中部署于人机协同论坛中。Kwame 2.0能够检索相关课程材料并生成上下文感知的响应，同时鼓励人类监督和社区参与。我们在一个持续15个月的纵向研究中部署了该系统，覆盖15个班级，3717名学生，35个非洲国家。通过社区反馈和专家评分评估发现，Kwame 2.0能够提供高质量和及时的支持，在课程相关问题上准确率较高，而人类指导者和同伴有效缓解了错误，尤其是在行政问题上。我们的发现表明，人机协同的生成式AI系统可以结合AI的可扩展性和速度与人类支持的可靠性，为资源受限环境下的少数群体提供有效的学习帮助。
英文摘要：
Providing timely and accurate learning support in large-scale online coding courses is challenging, particularly in resource-constrained contexts. We present Kwame 2.0, a bilingual (English-French) generative AI teaching assistant built using retrieval-augmented generation and deployed in a human-in-the-loop forum within SuaCode, an introductory mobile-based coding course for learners across Africa. Kwame 2.0 retrieves relevant course materials and generates context-aware responses while encouraging human oversight and community participation. We deployed the system in a 15-month longitudinal study spanning 15 cohorts with 3,717 enrollments across 35 African countries. Evaluation using community feedback and expert ratings shows that Kwame 2.0 provided high-quality and timely support, achieving high accuracy on curriculum-related questions, while human facilitators and peers effectively mitigated errors, particularly for administrative queries. Our findings demonstrate that human-in-the-loop generative AI systems can combine the scalability and speed of AI with the reliability of human support, offering an effective approach to learning assistance for underrepresented populations in resource-constrained settings at scale.
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。
