Abstract
Automatic math correction aims to check students' solutions to mathematical problems via artificial intelligence technologies. Most existing studies focus on judging the final answer at the problem level, while they ignore detailed feedback on each step in a math problem-solving process, which requires abilities of semantic understanding and reasoning. In this paper, we propose a reinforcement learning (RL)-based method to boost large language model (LLM) for step-level automatic math correction, named StepAMC. Particularly, we convert the step-level automatic math correction within the text classification task into an RL problem to enhance the reasoning capabilities of LLMs. Then, we design a space-constrained policy network to improve the stability of RL. Then, we introduce a fine-grained reward network to convert the binary human feedback into a continuous value. We conduct extensive experiments over two benchmark datasets and the results show that our model outperforms the eleven strong baselines.
Abstract (translated)
自动数学纠错旨在通过人工智能技术检查学生解答数学问题的过程。现有大多数研究主要集中在评判每个问题的最终答案，而忽视了对解决问题过程中每一步的具体反馈，这需要具备语义理解和推理的能力。本文提出了一种基于强化学习（RL）的方法来增强大语言模型（LLM），用于步骤级别的自动数学纠错，并将其命名为StepAMC。特别地，我们将文本分类任务中的步骤级自动数学纠错问题转化为一个RL问题，以提升LLMs的推理能力。然后设计了一个空间受限的策略网络，以提高RL的稳定性。接着引入了一种细粒度奖励网络，将二元人类反馈转换为连续值。我们在两个基准数据集上进行了广泛的实验，并且结果显示我们的模型优于11个强大的基线模型。
URL
https://arxiv.org/abs/2503.18432
