Work

Commonsense Knowledge with Negation: A Resource to Enhance Negation Understanding

Year: 2026

Type: conference-paper

Abstract: Negation is a common and important semantic feature in natural language, yet Large Language Models (LLMs) struggle when negation is involved in natural language understanding tasks.Commonsense knowledge, on the other hand, despite being a well-studied topic, lacks investigations involving negation.In this work, we show that commonsense knowledge with negation is challenging for models to understand.We present a novel approach to automatically augment existing commonsense knowledge corpora with negation, yielding two new corpora containing over 2M triples with if-then relations.In addition, pre-training LLMs on our corpora benefits negation understanding.

Source: Findings of the Association for Computational Linguistics: ACL (Findings of ACL)

DOI: 10.18653/v1/2026.findings-acl.578

Authors: Zijie Wang, MohammadHossein Rezaei, Farzana Rashid, Eduardo Blanco

Institutions: University of Arizona, University of North Carolina at Asheville

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: National Science Foundation

Award: CAREER: Understanding Negation in Positive Terms