DualReward: A Dynamic Reinforcement Learning Framework for Cloze Tests Distractor Generation
Abstract
This paper introduces DualReward, a novel reinforcement learning framework for automatic distractor generation in cloze tests. Unlike conventional approaches that rely primarily on supervised learning or static generative models, our method employs a dual reward structure with adaptive scaling that differentiates between human-created gold standard distractors and model-generated candidates. The framework dynamically adjusts reward signal intensity based on model performance and confidence. We evaluate our approach on both passage-level (CLOTH-F) and sentence-level (MCQ) cloze test datasets, demonstrating consistent improvements over state-of-the-art baselines. Experimental results show that our adaptive reward scaling mechanism provides modest but consistent benefits on homogeneous datasets (CLOTH-F) and more substantial improvements (3.48-3.86% in P@1) on diverse, cross-domain data (MCQ), suggesting its particular effectiveness for handling varied question types and domains. Our work offers a flexible framework that effectively balances learning from reliable human examples while exploring novel, high-quality distractors for automated test generation.
Cite
@article{arxiv.2507.11875,
title = {DualReward: A Dynamic Reinforcement Learning Framework for Cloze Tests Distractor Generation},
author = {Tianyou Huang and Xinglu Chen and Jingshen Zhang and Xinying Qiu and Ruiying Niu},
journal= {arXiv preprint arXiv:2507.11875},
year = {2025}
}
Comments
Accepted to CCL 2025