Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Isabel Molnar, Peiyu Li, Si Chen, Sugana Chawla, James Lang, Ronald Metoyer, Ting Hua, Nitesh V. Chawla

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.

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

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.
Paper Structure (12 sections, 1 equation, 4 figures, 1 table)

This paper contains 12 sections, 1 equation, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Works
  3. Pipeline of TeachingCoach
  4. Rules Extraction
  5. Data Collection
  6. Pedagogically-Grounded Model Training
  7. Evaluation
  8. Demo System
  9. Preliminary User Study and Results
  10. Study Design
  11. Findings
  12. Discussion and Conclusion

Figures (4)

  • Figure 1: Pipeline of TeachingCoach. Teaching guidelines are extracted from education resources, while GPT-4o generates teacher profiles and teaching challenges. These inputs prompt GPT-4o to produce synthetic multi-turn conversations, which, after expert filtering, are used to fine-tune a LLaMA model deployed as the TeachingCoach chatbot.
  • Figure 2: The onboarding asks users to specific their experience, current courses, and AI attitudes
  • Figure 3: The chatbot interface allows users to interact with the TeachingCoach model, demonstrating multi-turn instructional support.
  • Figure 4: The dashboard provides a window for users to schedule consultations with live experts, view the resources they have collected, and manage their stored data