arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.09609cs.CLcs.AI
收藏

LogicPrpBank:一个用于逻辑蕴涵与等价的语料库

LogicPrpBank: A Corpus for Logical Implication and Equivalence

University of Pittsburgh(匹兹堡大学);Emory University(埃默里大学)

Zhexiong Liu, Jing Zhang, Jiaying Lu, Wenjing Ma, Joyce C Ho

AI总结:

本文提出了标注良好的命题逻辑语料库LogicPrpBank,包含跨六个学科的7093个命题逻辑陈述,用于研究逻辑蕴涵与等价推理任务,基准测试表明该语料库为模型改进提供了有用资源。

摘要:

逻辑推理在问题解决和决策制定中一直被迫切需要。尽管语言模型(LMs)已展现出处理多种推理任务(例如,常识推理)的能力,但它们推理复杂数学问题,特别是命题逻辑的能力,在很大程度上仍未被探索。这种探索的缺乏可归因于标注语料库的有限可用性。在此,我们提出了一个标注良好的命题逻辑语料库 LogicPrpBank,包含跨六个数学学科的 7093 个命题逻辑陈述(PLSs),以研究推理逻辑蕴涵与等价的全新任务。我们用广泛使用的 LMs 对 LogicPrpBank 进行基准测试,以表明我们的语料库为这一具有挑战性的任务提供了有用的资源,并且模型仍有充足的改进空间。

英文摘要:

Logic reasoning has been critically needed in problem-solving and decision-making. Although Language Models (LMs) have demonstrated capabilities of handling multiple reasoning tasks (e.g., commonsense reasoning), their ability to reason complex mathematical problems, specifically propositional logic, remains largely underexplored. This lack of exploration can be attributed to the limited availability of annotated corpora. Here, we present a well-labeled propositional logic corpus, LogicPrpBank, containing 7093 Propositional Logic Statements (PLSs) across six mathematical subjects, to study a brand-new task of reasoning logical implication and equivalence. We benchmark LogicPrpBank with widely-used LMs to show that our corpus offers a useful resource for this challenging task and there is ample room for model improvement.

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。

↑