Expanding a free content library for an open-source adaptive tutoring system using large language models
Zachary Pardos, Professor
School of Information and Education
Applications for Fall 2024 are closed for this project.
Adaptive tutoring systems are designed to provide students in K-12 and intro college courses a personalized homework experience. This means giving the right problem to a student at the right time based given a continuous assessment of their mastery of a skill. At Berkeley, the ALEKS system is used to bridge gaps in Mathematics knowledge between high school and college. These systems are effective but costly and this cost represents an impediment to equitable education, since not all parents and districts can afford this type of product. The Computational Approaches to Human Learning research lab is working on an open-source version of this type of tutoring system. The code-base for the tutoring system has been established, but the content is currently limited. This project calls on students with interests in teaching, technology, equity, and machine learning to draw on open license educational content on the internet (called open educational resources) and natural language AI models (i.e., ChatGPT) to help build-out the content pool for this open-source system.
Role: The role would involve (1) transcribing educational content from the web into a Google spreadsheet format amenable to the adaptive tutoring platform (2) periodically creating new tutorial content from scratch or using an AI model to assist and (3) editing testing, and quality checking educational content transcribed by a network of qualified volunteers.
Learning outcomes include (a) understanding what adaptive tutoring is and the various components of this educational technology and (b) learning effective pedagogical/teaching practices in an increasingly digital world (c) learning the limits and utility of modern natural language processing models.
Qualifications: Applicants must have an interest in education, technology, and equity. Teaching or tutoring experience in STEM is recommended.
No technical/programming skills are required; however, if you have a background in NLP, please note that and you could contribute to testing new language models used for generating tutor hints.
Day-to-day supervisor for this project: Ioannis Anastasopoulos, Graduate Student
Hours: 6-8 hrs
Off-Campus Research Site: Remote
Related website: https://arxiv.org/abs/2302.06871
Related website: https://arxiv.org/abs/2302.06871