analiza aiqbench
This research introduces CoSC, a novel LLM-based framework for knowledge graph completion that effectively merges discrete structural coding with similarity-based entity refinement. By addressing the historical separation of these two approaches, the method achieves superior performance on standard benchmarks like FB15k-237 while maintaining competitive results across other metrics. The work represents a significant step forward in leveraging large language models to better navigate complex relational structures without relying on restricted candidate sets.
LLM-Based Knowledge Graph Completion Combining Discrete Structural Coding with Similar Entity Information
arXiv:2608.30235v1 Announce Type: new 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.
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.
Artificial Intelligence (cs.AI)
arXiv:2608.30235 [cs.AI]
(or arXiv:2608.30235v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2608.30235 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 197 cuvinte
Subiecte conexe
Lattice-Based Cryptography Explained
Quantum Zeitgeist · 15 aug. 2026
From Vector Search to Agentic RAG: Building an Enterprise Research Analyst with hipVS
AMD · 15 iul. 2026
Hyperloom: A Multi-Agent Harness for Autonomous Inference Optimization on AMD GPUs
AMD · 21 sept. 2026
The SaaSpocalypse that wasn’t, with Atlassian CEO Mike Cannon-Brookes
The Verge · 28 sept. 2026