LLM-Based Knowledge Graph Completion Combining Discrete Structural Coding with Similar Entity Information
cs.AI
Submitted: 2026-08-31
Updated: 2026-08-31
Comments: Accepted by ISWC 26 Posters and Demos Track
License: http://creativecommons.org/licenses/by/4.0/
The gist: Knowledge graph completion requires models to use both textual descriptions and relational structure.
Terminology
Abstract
Knowledge graph completion requires models to use both textual descriptions and relational structure. Existing LLM-based methods either encode KG structure as discrete tokens or refine a restricted set of candidate entities, and these two directions have largely been studied separately. We propose CoSC for LLM-based KGC, which combines discrete structural coding with similar entity information. Specifically, an LLM generates an initial candidate entity ranking from discrete structural codes, after which information from entities with structures similar to that of the query entity refines the ranking. Experiments on FB15k-237 show that CoSC outperforms existing baselines on MRR and Hits@10 while remaining competitive on Hits@1.
Sources
- KARMA: Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichment
- OMNIA: Closing the Loop by Leveraging LLMs for Knowledge Graph Completion
- KG-BERT: BERT for Knowledge Graph Completion
- The Llama 3 Herd of Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection