KG-CF: Knowledge Graph Completion with Context Filtering under the Guidance of Large Language Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zheng, Zaiyi, Dong, Yushun, Wang, Song, Liu, Haochen, Wang, Qi, Li, Jundong
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916552249442304
author Zheng, Zaiyi
Dong, Yushun
Wang, Song
Liu, Haochen
Wang, Qi
Li, Jundong
author_facet Zheng, Zaiyi
Dong, Yushun
Wang, Song
Liu, Haochen
Wang, Qi
Li, Jundong
contents Large Language Models (LLMs) have shown impressive performance in various tasks, including knowledge graph completion (KGC). However, current studies mostly apply LLMs to classification tasks, like identifying missing triplets, rather than ranking-based tasks, where the model ranks candidate entities based on plausibility. This focus limits the practical use of LLMs in KGC, as real-world applications prioritize highly plausible triplets. Additionally, while graph paths can help infer the existence of missing triplets and improve completion accuracy, they often contain redundant information. To address these issues, we propose KG-CF, a framework tailored for ranking-based KGC tasks. KG-CF leverages LLMs' reasoning abilities to filter out irrelevant contexts, achieving superior results on real-world datasets. The code and datasets are available at \url{https://anonymous.4open.science/r/KG-CF}.
format Preprint
id arxiv_https___arxiv_org_abs_2501_02711
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle KG-CF: Knowledge Graph Completion with Context Filtering under the Guidance of Large Language Models
Zheng, Zaiyi
Dong, Yushun
Wang, Song
Liu, Haochen
Wang, Qi
Li, Jundong
Artificial Intelligence
Computation and Language
Large Language Models (LLMs) have shown impressive performance in various tasks, including knowledge graph completion (KGC). However, current studies mostly apply LLMs to classification tasks, like identifying missing triplets, rather than ranking-based tasks, where the model ranks candidate entities based on plausibility. This focus limits the practical use of LLMs in KGC, as real-world applications prioritize highly plausible triplets. Additionally, while graph paths can help infer the existence of missing triplets and improve completion accuracy, they often contain redundant information. To address these issues, we propose KG-CF, a framework tailored for ranking-based KGC tasks. KG-CF leverages LLMs' reasoning abilities to filter out irrelevant contexts, achieving superior results on real-world datasets. The code and datasets are available at \url{https://anonymous.4open.science/r/KG-CF}.
title KG-CF: Knowledge Graph Completion with Context Filtering under the Guidance of Large Language Models
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2501.02711