EMNLP Findings2025
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 (Structure-aware Language model with Injection and coNtrastive Training), 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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Learning to Think on Hypergraph: HyperCoT for Structure-Guided N-ary Knowledge Graph Completion cites LoRA: Low-Rank Adaptation of Large Language Models
- GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion cites LoRA: Low-Rank Adaptation of Large Language Models
- GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion cites Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
- GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion cites Composition-based Multi-Relational Graph Convolutional Networks
- Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction cites Composition-based Multi-Relational Graph Convolutional Networks
Cited by top-tier papers2
- Learning to Think on Hypergraph: HyperCoT for Structure-Guided N-ary Knowledge Graph CompletionMengxue Yang, Jinming Li, Chun Yang, Jiaqi Zhu et al.ACL 2026
- GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph CompletionQizhuo Xie, Yunhui Liu, Yu Xing, Qianzi Hou et al.ACL 2026
Builds on11
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
- Composition-based Multi-Relational Graph Convolutional NetworksShikhar Vashishth, Soumya Sanyal, Vikram Nitin, Partha P. TalukdarICLR 2020 · 1,105 citations
- Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link PredictionZhaocheng Zhu, Zuobai Zhang, Louis-Pascal A. C. Xhonneux, Jian TangNeurIPS 2021 · 546 citations
- Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base EmbeddingsApoorv Saxena, Aditay Tripathi, Partha P. TalukdarACL 2020 · 488 citations
Related papers
- Logic-Aware Knowledge Graph Reasoning for Structural Sparsity under Large Language Model SupervisionYudai Pan, Jiajie Hong, Tianzhe Zhao, Lingyun Song et al.WWW 2025 · 1 citation
- Making Large Language Models Perform Better in Knowledge Graph CompletionYichi Zhang, Zhuo Chen, Lingbing Guo, Yajing Xu et al.ACM MM 2024 · 86 citations
- MAKI: Multi-layer Aligned Knowledge Injection for Structure-aware Knowledge Graph Completion with Large Language ModelsZhiwen Xie, Xin Wang, Guangyou Zhou, Derek F. WongACL Findings 2026
- DrKGC: Dynamic Subgraph Retrieval-Augmented LLMs for Knowledge Graph Completion across General and Biomedical DomainsYongkang Xiao, Sinian Zhang, Yi Dai, Huixue Zhou et al.EMNLP Findings 2025 · 6 citations
- Enhancing Large Language Model for Knowledge Graph Completion via Structure-Aware Alignment-TuningYu Liu, Yanan Cao, Xixun Lin, Yanmin Shang et al.EMNLP 2025 · 2 citations
