Saved in:
Bibliographic Details
Main Authors: Guevarra, Michael, Bhattacharjee, Indronil, Das, Srijita, Wayllace, Christabel, Epp, Carrie Demmans, Taylor, Matthew E., Tay, Alan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.09870
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916569399951360
author Guevarra, Michael
Bhattacharjee, Indronil
Das, Srijita
Wayllace, Christabel
Epp, Carrie Demmans
Taylor, Matthew E.
Tay, Alan
author_facet Guevarra, Michael
Bhattacharjee, Indronil
Das, Srijita
Wayllace, Christabel
Epp, Carrie Demmans
Taylor, Matthew E.
Tay, Alan
contents Social skills training targets behaviors necessary for success in social interactions. However, traditional classroom training for such skills is often insufficient to teach effective communication -- one-to-one interaction in real-world scenarios is preferred to lecture-style information delivery. This paper introduces a framework that allows instructors to collaborate with large language models to dynamically design realistic scenarios for students to communicate. Our framework uses these scenarios to enable student rehearsal, provide immediate feedback, and visualize performance for both students and instructors. Unlike traditional intelligent tutoring systems, instructors can easily co-create scenarios with a large language model without technical skills. Additionally, the system generates new scenario branches in real time when existing options do not fit the student's response.
format Preprint
id arxiv_https___arxiv_org_abs_2501_09870
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An LLM-Guided Tutoring System for Social Skills Training
Guevarra, Michael
Bhattacharjee, Indronil
Das, Srijita
Wayllace, Christabel
Epp, Carrie Demmans
Taylor, Matthew E.
Tay, Alan
Machine Learning
Social skills training targets behaviors necessary for success in social interactions. However, traditional classroom training for such skills is often insufficient to teach effective communication -- one-to-one interaction in real-world scenarios is preferred to lecture-style information delivery. This paper introduces a framework that allows instructors to collaborate with large language models to dynamically design realistic scenarios for students to communicate. Our framework uses these scenarios to enable student rehearsal, provide immediate feedback, and visualize performance for both students and instructors. Unlike traditional intelligent tutoring systems, instructors can easily co-create scenarios with a large language model without technical skills. Additionally, the system generates new scenario branches in real time when existing options do not fit the student's response.
title An LLM-Guided Tutoring System for Social Skills Training
topic Machine Learning
url https://arxiv.org/abs/2501.09870