用大模型过滤无关信息，提升知识图谱补全的排序效果
KG-CF: Knowledge Graph Completion with Context Filtering under the Guidance of Large Language Models
- 利用大模型推理能力筛选图谱路径中的冗余信息
- 在真实数据集上显著优于现有方法，提升补全准确性
- 适合需要高置信度三元组的工业级知识图谱应用
大语言模型在多项任务中表现优异，包括知识图谱补全（KGC）。然而，现有研究多将大模型用于分类任务（如识别缺失三元组），而非基于排序的任务——即根据合理性对候选实体进行排序。这一局限限制了大模型在实际应用中的价值，因真实场景更关注高度可信的三元组。此外，虽然图谱路径有助于推断缺失三元组并提升补全准确率，但常包含冗余信息。为此，我们提出KG-CF框架，专为基于排序的KGC任务设计。该框架利用大模型的推理能力，有效过滤无关上下文，在真实数据集上取得更优结果。代码与数据集已公开于 <https://anonymous.4open.science/r/KG-CF>。
原文摘要 · Abstract (English)
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}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。