Abstract
This paper presents the ADAIO team’s system entry in the Building Educational Applications (BEA) 2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues. The task aims to assess the performance of state-of-the-art generative models as AI teachers in producing suitable responses within a student-teacher dialogue. Our system comprises evaluating various baseline models using OpenAI GPT-3 and designing diverse prompts to prompt the OpenAI models for teacher response generation. After the challenge, our system achieved second place by employing a few-shot prompt-based approach with the OpenAI text-davinci-003 model. The results highlight the few-shot learning capabilities of large-language models, particularly OpenAI’s GPT-3, in the role of AI teachers.- Anthology ID:
- 2023.bea-1.65
- Volume:
- Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Ekaterina Kochmar, Jill Burstein, Andrea Horbach, Ronja Laarmann-Quante, Nitin Madnani, Anaïs Tack, Victoria Yaneva, Zheng Yuan, Torsten Zesch
- Venue:
- BEA
- SIG:
- SIGEDU
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 796–804
- Language:
- URL:
- https://aclanthology.org/2023.bea-1.65
- DOI:
- 10.18653/v1/2023.bea-1.65
- Cite (ACL):
- Adaeze Adigwe and Zheng Yuan. 2023. The ADAIO System at the BEA-2023 Shared Task: Shared Task Generating AI Teacher Responses in Educational Dialogues. In Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023), pages 796–804, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- The ADAIO System at the BEA-2023 Shared Task: Shared Task Generating AI Teacher Responses in Educational Dialogues (Adigwe & Yuan, BEA 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2023.bea-1.65.pdf