SCE: Semantic Consistency Enhanced Reinforcement Learning for Multi-Hop Knowledge Graph Reasoning

Yanwen Huang, Yao Liu, Qiao Liu, Rui Hou, Tingting Dai


Abstract
Multi-hop reasoning with reinforcement learning has proven effective in discovering inference paths in incomplete knowledge graphs. However, a major challenge remains: spurious paths (incorrect reasoning paths that accidentally lead to correct answers) often arise due to reward mechanisms that prioritize final results over reasoning quality. While existing approaches attempt to mitigate this issue using external rules, they often neglect the internal semantic consistency between the target triple and the intermediate triples along the reasoning path. In this paper, we propose a novel framework, Semantic Consistency Enhanced Reinforcement Learning (SCE), which incorporates semantic consistency into the reward function to guide multi-hop reasoning. Experimental results demonstrate that SCE outperforms strong baseline methods and facilitates the discovery of more interpretable reasoning paths.
Anthology ID:
2025.findings-emnlp.289
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5413–5425
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.289/
DOI:
Bibkey:
Cite (ACL):
Yanwen Huang, Yao Liu, Qiao Liu, Rui Hou, and Tingting Dai. 2025. SCE: Semantic Consistency Enhanced Reinforcement Learning for Multi-Hop Knowledge Graph Reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 5413–5425, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
SCE: Semantic Consistency Enhanced Reinforcement Learning for Multi-Hop Knowledge Graph Reasoning (Huang et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.289.pdf
Checklist:
 2025.findings-emnlp.289.checklist.pdf