Be My Mate: Simulating Virtual Students for collaboration using Large Language Models

Sergi Solera-Monforte, Pablo Arnau-González, Miguel Arevalillo-Herráez


Abstract
Advancements in machine learning, particularly Large Language Models (LLMs), offer new opportunities for enhancing education through personalized assistance. We introduce “Be My Mate,” an agent that leverages LLMs to simulate virtual peer students in online collaborative education. The system includes a subscription module for real-time updates and a conversational module for generating supportive interactions. Key challenges include creating temporally realistic interactions and credible error generation. The initial demonstration shows promise in enhancing student engagement and learning outcomes.
Anthology ID:
2024.inlg-demos.1
Volume:
Proceedings of the 17th International Natural Language Generation Conference: System Demonstrations
Month:
September
Year:
2024
Address:
Tokyo, Japan
Editors:
Saad Mahamood, Nguyen Le Minh, Daphne Ippolito
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–3
Language:
URL:
https://aclanthology.org/2024.inlg-demos.1
DOI:
Bibkey:
Cite (ACL):
Sergi Solera-Monforte, Pablo Arnau-González, and Miguel Arevalillo-Herráez. 2024. Be My Mate: Simulating Virtual Students for collaboration using Large Language Models. In Proceedings of the 17th International Natural Language Generation Conference: System Demonstrations, pages 1–3, Tokyo, Japan. Association for Computational Linguistics.
Cite (Informal):
Be My Mate: Simulating Virtual Students for collaboration using Large Language Models (Solera-Monforte et al., INLG 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.inlg-demos.1.pdf