ACL Findings2026
MAKI: Multi-layer Aligned Knowledge Injection for Structure-aware Knowledge Graph Completion with Large Language Models
Abstract
Recent advances in large language models (LLMs) have shown strong potential for knowledge graph completion (KGC). However, existing LLM-based approaches often struggle to effectively capture the structural information in knowledge graphs (KGs), leading to suboptimal reasoning performance. To address this challenge, we propose a Multi-layer Aligned Knowledge Injection (MAKI) model, a novel method that tightly integrates structured KG information into LLMs through multi-layer alignment. Specifically, we first leverage LLMs to encode the textual information of entities and relations, obtaining their semantic representations across multiple hidden layers. We then introduce a multi-layer aligned structure learning module, which uses graph neural networks (GNNs) to learn relational structures while aligning with the corresponding LLM layers to bridge the gap between structural and semantic spaces. Finally, a gated fusion mechanism is used to inject the structured knowledge into the LLM for reasoning over candidate triples. Experimental results on various benchmark datasets demonstrate that the proposed MAKI outperforms existing state-of-theart methods.
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.
Lineage
- Do Pre-trained Models Benefit Knowledge Graph Completion? A Reliable Evaluation and a Reasonable Approach cites CoDEx: A Comprehensive Knowledge Graph Completion Benchmark
- Communicative Message Passing for Inductive Relation Reasoning cites Inductive Relation Prediction by Subgraph Reasoning
Builds on18
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- Inductive Relation Prediction by Subgraph ReasoningKomal K. Teru, Etienne G. Denis, William L. HamiltonICML 2020 · 493 citations
- Communicative Message Passing for Inductive Relation ReasoningSijie Mai, Shuangjia Zheng, Yuedong Yang, Haifeng HuAAAI 2021 · 136 citations
- Do Pre-trained Models Benefit Knowledge Graph Completion? A Reliable Evaluation and a Reasonable ApproachXin Lv, Yankai Lin, Yixin Cao, Lei Hou et al.ACL Findings 2022 · 97 citations
- CoDEx: A Comprehensive Knowledge Graph Completion BenchmarkTara Safavi, Danai KoutraEMNLP 2020 · 97 citations
Related papers
- 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
- Making Large Language Models Perform Better in Knowledge Graph CompletionYichi Zhang, Zhuo Chen, Lingbing Guo, Yajing Xu et al.ACM MM 2024 · 86 citations
- Joint Multilingual Knowledge Graph Completion and AlignmentVinh Tong, Dat Quoc Nguyen, Trung Thanh Huynh, Tam Thanh Nguyen et al.EMNLP Findings 2022 · 7 citations
- HFR-MKGC: Hierarchical Fusion Reasoning with MLLMs for Multi-modal Knowledge Graph CompletionDi Wang, Junping Du, Zhe Xue, Meiyu Liang et al.AAAI 2026
- A New Pipeline for Knowledge Graph Reasoning Enhanced by Large Language Models Without Fine-TuningZhongwu Chen, Long Bai, Zixuan Li, Zhen Huang et al.EMNLP 2024 · 3 citations
