Improving Socratic Question Generation using Data Augmentation and Preference Optimization

Nischal Ashok Kumar, Andrew Lan


Abstract
The Socratic method is a way of guiding students toward solving a problem independently without directly revealing the solution to the problem by asking incremental questions. Although this method has been shown to significantly improve student learning outcomes, it remains a complex labor-intensive task for instructors. Large language models (LLMs) can be used to augment human effort by automatically generating Socratic questions for students. However, existing methods that involve prompting these LLMs sometimes produce invalid outputs, e.g., those that directly reveal the solution to the problem or provide irrelevant or premature questions. To alleviate this problem, inspired by reinforcement learning with AI feedback (RLAIF), we first propose a data augmentation method to enrich existing Socratic questioning datasets with questions that are invalid in specific ways. Also, we propose a method to optimize open-source LLMs such as LLama 2 to prefer ground-truth questions over generated invalid ones, using direct preference optimization (DPO). Our experiments on a Socratic questions dataset for student code debugging show that a DPO-optimized LLama 2-7B model can effectively avoid generating invalid questions, and as a result, outperforms existing state-of-the-art prompting methods.
Anthology ID:
2024.bea-1.10
Volume:
Proceedings of the 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2024)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Ekaterina Kochmar, Marie Bexte, Jill Burstein, Andrea Horbach, Ronja Laarmann-Quante, Anaïs Tack, Victoria Yaneva, Zheng Yuan
Venue:
BEA
SIG:
SIGEDU
Publisher:
Association for Computational Linguistics
Note:
Pages:
108–118
Language:
URL:
https://aclanthology.org/2024.bea-1.10
DOI:
Bibkey:
Cite (ACL):
Nischal Ashok Kumar and Andrew Lan. 2024. Improving Socratic Question Generation using Data Augmentation and Preference Optimization. In Proceedings of the 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2024), pages 108–118, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Improving Socratic Question Generation using Data Augmentation and Preference Optimization (Ashok Kumar & Lan, BEA 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.bea-1.10.pdf