Saved in:
Bibliographic Details
Main Authors: Liu, Zhexiong, Zhang, Jing, Lu, Jiaying, Ma, Wenjing, Ho, Joyce C
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.09609
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929244214394880
author Liu, Zhexiong
Zhang, Jing
Lu, Jiaying
Ma, Wenjing
Ho, Joyce C
author_facet Liu, Zhexiong
Zhang, Jing
Lu, Jiaying
Ma, Wenjing
Ho, Joyce C
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_09609
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LogicPrpBank: A Corpus for Logical Implication and Equivalence
Liu, Zhexiong
Zhang, Jing
Lu, Jiaying
Ma, Wenjing
Ho, Joyce C
Computation and Language
Artificial Intelligence
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.
title LogicPrpBank: A Corpus for Logical Implication and Equivalence
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2402.09609