Metraipolis › archive › dc_ca5db469a61d
LLM-Based Knowledge Graph Completion Combining Discrete Structural Coding with Similar Entity Information — arXiv:2608.30235
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.30235
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:44:35.228Z
- SHA-256 of the archived text
58de6377a10c1244ee7c698615658db20fd54ae566fcb4318bae8363f2a0d2d2- Stable URL of this page
https://metraipolis.com/documento/dc_ca5db469a61d
How to cite
LLM-Based Knowledge Graph Completion Combining Discrete Structural Coding with Similar Entity Information — arXiv:2608.30235 — arXiv (en), https://arxiv.org/abs/2608.30235 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca5db469a61d (Metraipolis archive dc_ca5db469a61d, sha256 58de6377a10c1244ee7c698615658db20fd54ae566fcb4318bae8363f2a0d2d2)
BibTeX
@misc{dcca5db469a61d,
title = {LLM-Based Knowledge Graph Completion Combining Discrete Structural Coding with Similar Entity Information — arXiv:2608.30235},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.30235},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca5db469a61d; sha256 58de6377a10c1244ee7c698615658db20fd54ae566fcb4318bae8363f2a0d2d2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30235. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.30235 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T07:28:26.592Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).