Abstract
This paper presents the results of our participation in the BEA 2023 shared task, which focuses on generating AI teacher responses in educational dialogues. We conducted experiments using several Open-Source Large Language Models (LLMs) and explored fine-tuning techniques along with prompting strategies, including Few-Shot and Chain-of-Thought approaches. Our best model was ranked 4.5 in the competition with a BertScore F1 of 0.71 and a DialogRPT final (avg) of 0.35. Nevertheless, our internal results did not exactly correlate with those obtained in the competition, which showed the difficulty in evaluating this task. Other challenges we faced were data leakage on the train set and the irregular format of the conversations.- Anthology ID:
- 2023.bea-1.61
- 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:
- 756–765
- Language:
- URL:
- https://aclanthology.org/2023.bea-1.61
- DOI:
- 10.18653/v1/2023.bea-1.61
- Cite (ACL):
- Alexis Baladón, Ignacio Sastre, Luis Chiruzzo, and Aiala Rosá. 2023. RETUYT-InCo at BEA 2023 Shared Task: Tuning Open-Source LLMs for Generating Teacher Responses. In Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023), pages 756–765, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- RETUYT-InCo at BEA 2023 Shared Task: Tuning Open-Source LLMs for Generating Teacher Responses (Baladón et al., BEA 2023)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2023.bea-1.61.pdf