arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.03877cs.CLcs.AI
收藏

超越直线与圆:揭示大型语言模型中的几何推理差距

Beyond Lines and Circles: Unveiling the Geometric Reasoning Gap in Large Language Models

University of Warsaw(华沙大学);Google DeepMind(谷歌DeepMind)

Spyridon Mouselinos, Henryk Michalewski, Mateusz Malinowski

AI总结:

本文揭示了大型语言模型在构造性几何问题求解中的几何推理差距,指出其在目标变量选择和2D空间关系处理上的不足,并提出通过内部对话驱动的多智能体系统框架,结合自我纠正与协作机制提升其几何推理能力。

摘要:

大型语言模型(LLMs)在数学和算法任务中展现出日益增强的能力,但其几何推理技能仍待深入探索。我们研究了LLMs在构造性几何问题求解中的能力,这是人类数学推理发展中最基础的步骤之一。我们的工作揭示了最先进的LLMs在该领域面临的显著挑战,尽管它们在类似领域取得了诸多成功。LLMs在目标变量选择上表现出偏差,且在处理2D空间关系时存在困难,经常错误表示并产生对象及其位置的幻觉。为此,我们引入了一个框架,构建基于LLMs的多智能体系统,通过进行内部对话来增强其现有的推理潜力。本研究强调了LLMs当前在几何推理方面的局限性,并通过自我纠正、协作和多样化角色专业化提升了其几何推理能力。

英文摘要:

Large Language Models (LLMs) demonstrate ever-increasing abilities in mathematical and algorithmic tasks, yet their geometric reasoning skills are underexplored. We investigate LLMs' abilities in constructive geometric problem-solving one of the most fundamental steps in the development of human mathematical reasoning. Our work reveals notable challenges that the state-of-the-art LLMs face in this domain despite many successes in similar areas. LLMs exhibit biases in target variable selection and struggle with 2D spatial relationships, often misrepresenting and hallucinating objects and their placements. To this end, we introduce a framework that formulates an LLMs-based multi-agents system that enhances their existing reasoning potential by conducting an internal dialogue. This work underscores LLMs' current limitations in geometric reasoning and improves geometric reasoning capabilities through self-correction, collaboration, and diverse role specializations.

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。

↑