KG-CF: Knowledge Graph Completion with Context Filtering under the Guidance of Large Language Models
This work addresses ranking-based KGC for real-world applications, but it is incremental as it builds on existing LLM methods by adapting them to a specific task bottleneck.
The paper tackles the problem of knowledge graph completion (KGC) by focusing on ranking-based tasks, which prioritize highly plausible triplets, and addresses the issue of redundant information in graph paths. The result is the KG-CF framework, which uses large language models (LLMs) to filter irrelevant contexts, achieving superior performance on real-world datasets.
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}.