arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.06232cs.AI
收藏

通过模拟人类双推理过程学习求解几何问题

Learning to Solve Geometry Problems via Simulating Human Dual-Reasoning Process

University of Science and Technology of China(中国科学技术大学);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(合肥综合性国家科学中心人工智能研究院);iFLYTEK AI Research(讯飞人工智能研究院);State Key Laboratory of Cognitive Intelligence(认知智能国家重点实验室)

Tong Xiao, Jiayu Liu, Zhenya Huang, Jinze Wu, Jing Sha, Shijin Wang, Enhong Chen

AI总结:

针对几何问题求解中编码器增强范式忽视人类推理特性的问题,本文提出DualGeoSolver,通过知识系统与推理系统迭代协作模拟人类双推理过程,并在GeoQA和GeoQA+上验证了准确率与鲁棒性优势。

摘要:

几何问题求解(Geometry Problem Solving, GPS)是一项经典且具有挑战性的数学问题,近年来受到广泛关注。它要求求解者全面理解文本和图形,掌握必要的几何知识,并在推理中恰当地加以应用。然而,现有工作遵循神经机器翻译范式,只关注增强编码器能力,忽视了人类几何推理的本质特征。本文受双过程理论启发,提出一种双推理几何求解器(Dual-Reasoning Geometry Solver, DualGeoSolver),用于模拟人类在GPS中的双推理过程。具体而言,我们在DualGeoSolver中构建了两个系统,即知识系统(Knowledge System)和推理系统(Inference System)。知识系统控制隐式推理过程,负责根据推理系统生成的逐步推理目标提供图形信息和几何知识。推理系统执行显式推理过程,明确每一步推理的目标,并应用知识生成用于解决该目标的程序token。两个系统迭代执行上述过程,其表现更符合人类认知。我们在GeoQA和GeoQA+两个基准数据集上进行了大量实验。结果表明,通过显式建模人类推理过程和知识应用,DualGeoSolver在求解准确率和鲁棒性方面均具有优越性。

英文摘要:

Geometry Problem Solving (GPS), which is a classic and challenging math problem, has attracted much attention in recent years. It requires a solver to comprehensively understand both text and diagram, master essential geometry knowledge, and appropriately apply it in reasoning. However, existing works follow a paradigm of neural machine translation and only focus on enhancing the capability of encoders, which neglects the essential characteristics of human geometry reasoning. In this paper, inspired by dual-process theory, we propose a Dual-Reasoning Geometry Solver (DualGeoSolver) to simulate the dual-reasoning process of humans for GPS. Specifically, we construct two systems in DualGeoSolver, namely Knowledge System and Inference System. Knowledge System controls an implicit reasoning process, which is responsible for providing diagram information and geometry knowledge according to a step-wise reasoning goal generated by Inference System. Inference System conducts an explicit reasoning process, which specifies the goal in each reasoning step and applies the knowledge to generate program tokens for resolving it. The two systems carry out the above process iteratively, which behaves more in line with human cognition. We conduct extensive experiments on two benchmark datasets, GeoQA and GeoQA+. The results demonstrate the superiority of DualGeoSolver in both solving accuracy and robustness from explicitly modeling human reasoning process and knowledge application.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑