TeachingCoach: A Fine-Tuned Scaffolding Chatbot for Instructional Guidance to Instructors

TL;DR

TeachingCoach is a specialized chatbot that provides real-time, pedagogically grounded guidance to higher education instructors, improving instructional support through a data-driven fine-tuning process and expert evaluation.

Contribution

The paper introduces TeachingCoach, a novel pedagogically grounded chatbot for instructor support, built using a data-centric pipeline and synthetic dialogue generation for fine-tuning.

Findings

TeachingCoach offers clearer, more reflective guidance than baseline models.

Expert evaluations favor TeachingCoach's pedagogical quality.

User study reveals trade-offs between conversational depth and efficiency.

Abstract

Higher education instructors often lack timely and pedagogically grounded support, as scalable instructional guidance remains limited and existing tools rely on generic chatbot advice or non-scalable teaching center human-human consultations. We present TeachingCoach, a pedagogically grounded chatbot designed to support instructor professional development through real-time, conversational guidance. TeachingCoach is built on a data-centric pipeline that extracts pedagogical rules from educational resources and uses synthetic dialogue generation to fine-tune a specialized language model that guides instructors through problem identification, diagnosis, and strategy development. Expert evaluations show TeachingCoach produces clearer, more reflective, and more responsive guidance than a GPT-4o mini baseline, while a user study with higher education instructors highlights trade-offs between conversational depth and interaction efficiency. Together, these results demonstrate that pedagogically grounded, synthetic data driven chatbots can improve instructional support and offer a scalable design approach for future instructional chatbot systems.