“Keep up the good work!”: Using Constraints in Zero Shot Prompting to Generate Supportive Teacher Responses

E. Margaret Perkoff, Angela Maria Ramirez, Sean von Bayern, Marilyn Walker, James Martin


Abstract
Educational dialogue systems have been used to support students and teachers for decades. Such systems rely on explicit pedagogically motivated dialogue rules. With the ease of integrating large language models (LLMs) into dialogue systems, applications have been arising that directly use model responses without the use of human-written rules, raising concerns about their use in classroom settings. Here, we explore how to constrain LLM outputs to generate appropriate and supportive teacher-like responses. We present results comparing the effectiveness of different constraint variations in a zero-shot prompting setting on a large mathematics classroom corpus. Generated outputs are evaluated with human annotation for Fluency, Relevance, Helpfulness, and Adherence to the provided constraints. Including all constraints in the prompt led to the highest values for Fluency and Helpfulness, and the second highest value for Relevance. The annotation results also demonstrate that the prompts that result in the highest adherence to constraints do not necessarily indicate higher perceived scores for Fluency, Relevance, or Helpfulness. In a direct comparison, all of the non-baseline LLM responses were ranked higher than the actual teacher responses in the corpus over 50% of the time.
Anthology ID:
2024.sigdial-1.11
Volume:
Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
September
Year:
2024
Address:
Kyoto, Japan
Editors:
Tatsuya Kawahara, Vera Demberg, Stefan Ultes, Koji Inoue, Shikib Mehri, David Howcroft, Kazunori Komatani
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
121–138
Language:
URL:
https://aclanthology.org/2024.sigdial-1.11
DOI:
10.18653/v1/2024.sigdial-1.11
Bibkey:
Cite (ACL):
E. Margaret Perkoff, Angela Maria Ramirez, Sean von Bayern, Marilyn Walker, and James Martin. 2024. “Keep up the good work!”: Using Constraints in Zero Shot Prompting to Generate Supportive Teacher Responses. In Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 121–138, Kyoto, Japan. Association for Computational Linguistics.
Cite (Informal):
“Keep up the good work!”: Using Constraints in Zero Shot Prompting to Generate Supportive Teacher Responses (Perkoff et al., SIGDIAL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.sigdial-1.11.pdf