SLiNT: Structure-aware Language Model with Injection and Contrastive Training for Knowledge Graph Completion

Mengxue Yang, Chun Yang, Jiaqi Zhu, Jiafan Li, Jingqi Zhang, Yuyang Li, Ying Li


Abstract
Link prediction in knowledge graphs (KGs) requires integrating structural information and semantic context to infer missing entities. While large language models (LLMs) offer strong generative reasoning capabilities, their limited exploitation of structural signals often results in *structural sparsity* and *semantic ambiguity*, especially under incomplete or zero-shot settings. To address these challenges, we propose **SLiNT** (**S**tructure-aware **L**anguage model with **I**njection and co**N**trastive **T**raining), a modular framework that injects KG-derived structural context into a frozen LLM backbone with lightweight LoRA-based adaptation for robust link prediction. Specifically, **Structure-Guided Neighborhood Enhancement (SGNE)** retrieves pseudo-neighbors to enrich sparse entities and mitigate missing context; **Dynamic Hard Contrastive Learning (DHCL)** introduces fine-grained supervision by interpolating hard positives and negatives to resolve entity-level ambiguity; and **Gradient-Decoupled Dual Injection (GDDI)** performs token-level structure-aware intervention while preserving the core LLM parameters. Experiments on WN18RR and FB15k-237 show that SLiNT achieves superior or competitive performance compared with both embedding-based and generation-based baselines, demonstrating the effectiveness of structure-aware representation learning for scalable knowledge graph completion.
Anthology ID:
2025.findings-emnlp.736
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:
13658–13671
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.736/
DOI:
Bibkey:
Cite (ACL):
Mengxue Yang, Chun Yang, Jiaqi Zhu, Jiafan Li, Jingqi Zhang, Yuyang Li, and Ying Li. 2025. SLiNT: Structure-aware Language Model with Injection and Contrastive Training for Knowledge Graph Completion. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 13658–13671, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
SLiNT: Structure-aware Language Model with Injection and Contrastive Training for Knowledge Graph Completion (Yang et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.736.pdf
Checklist:
 2025.findings-emnlp.736.checklist.pdf