LogiGraph: Logical Reasoning with Contrastive Learning and Lightweight Graph Networks

Xiang Li, Chen Shi, Yong Xu, Jun Huang


Abstract
Logical reasoning is a crucial factor in machine reading comprehension tasks (MRC). Existing methods suffer from the balance between semantic and explicit logical relation representations, in which some emphasize contextual semantics, while others pay more attention to explicit logical features. Additionally, previous methods utilize graph convolutional networks (GCN) for node updates, still exhibiting some shortcomings. To address these challenges, in this paper, we propose a logical reasoning method with contrastive learning and lightweight graph networks (LogiGraph). Our method focuses on the lightweight aspect of the GCN, which greatly improves the shortcomings of the GCN, and employs conjunction and punctuation marks as two types of edges to construct a dual graph. Besides, we combine contrastive learning with graph reasoning, which changes the logical expression’s content as the negative sample of the original context, enabling the model to capture negative logical relationships and improving generalization ability. We conduct extensive experiments on two public datasets, ReClor and LogiQA. Experimental results demonstrate that LogiGraph can achieve state-of-the-art performance on both datasets.
Anthology ID:
2025.coling-main.72
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1069–1079
Language:
URL:
https://aclanthology.org/2025.coling-main.72/
DOI:
Bibkey:
Cite (ACL):
Xiang Li, Chen Shi, Yong Xu, and Jun Huang. 2025. LogiGraph: Logical Reasoning with Contrastive Learning and Lightweight Graph Networks. In Proceedings of the 31st International Conference on Computational Linguistics, pages 1069–1079, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
LogiGraph: Logical Reasoning with Contrastive Learning and Lightweight Graph Networks (Li et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.72.pdf