Chain-of-Quizzes: Pedagogy-inspired Example Selection in In-Context-Learning

Yiquan Wu, Anlai Zhou, Yuhang Liu, Yifei Liu, Adam Jatowt, Weiming Lu, Jun Xiao, Kun Kuang


Abstract
In-context learning (ICL) has emerged as a powerful tool for enhancing large language models (LLMs) in addressing downstream tasks. In this paper, we explore the vital task of example selection in ICL by mimicking the human learning process. We propose a Chain-of-Quizzes (CoQ) framework inspired by educational theories such as Bruner’s Spiral Learning and Mastery Learning theory. Specifically, our framework employs the LLMs to answer the quiz (question in the example) to sift ‘good’ examples, combines these examples iteratively with the increasing complexity, and utilizes a final exam to gauge the combined example chains. Our extensive experiments on diverse reasoning datasets show the proposed approach outperforms baseline models. These findings underscore the framework’s potential for future research.
Anthology ID:
2024.findings-acl.603
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10136–10142
Language:
URL:
https://aclanthology.org/2024.findings-acl.603
DOI:
10.18653/v1/2024.findings-acl.603
Bibkey:
Cite (ACL):
Yiquan Wu, Anlai Zhou, Yuhang Liu, Yifei Liu, Adam Jatowt, Weiming Lu, Jun Xiao, and Kun Kuang. 2024. Chain-of-Quizzes: Pedagogy-inspired Example Selection in In-Context-Learning. In Findings of the Association for Computational Linguistics: ACL 2024, pages 10136–10142, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Chain-of-Quizzes: Pedagogy-inspired Example Selection in In-Context-Learning (Wu et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.603.pdf