LogicPrpBank: A Corpus for Logical Implication and Equivalence
This provides a new dataset for evaluating logical reasoning in language models, addressing a gap in mathematical problem-solving, but it is incremental as it focuses on data creation rather than novel methods.
The authors tackled the lack of annotated corpora for propositional logic reasoning by creating LogicPrpBank, a dataset with 7093 statements across six subjects, and benchmarked it with language models to show it is a useful resource with room for improvement.
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.