用大模型构建对齐维基数据的高质量知识图谱，提升推理准确性。
Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models
- 分阶段构建图谱，融合维基数据类型与关系约束
- 在MuSiQue上96%答案实体被覆盖，性能媲美带上下文的基线
- 高效且可扩展，构建仅需不足1000个输出词元
知识图谱为大语言模型提供结构化、可验证的语义支撑，但现有基于大模型的方法多将其作为文本检索的辅助结构，未充分挖掘其内在质量。本文提出Wikontic，一种多阶段流水线，从开放域文本中提取含限定词的候选三元组，强制执行维基数据的类型与关系约束，并通过实体归一化减少重复。生成的图谱紧凑、符合本体、连接紧密；在MuSiQue数据集上，正确答案实体出现在96%的生成三元组中。在HotpotQA上，仅使用三元组的设置达到76.0 F1，MuSiQue上达59.8 F1，匹配或超越多个依赖文本上下文的检索增强生成基线。此外，在MINE-1基准上信息保留率达86%，优于以往方法。构建过程高效：图谱生成少于1000个输出词元，约为AriGraph的3倍，GraphRAG的1/20。该流程显著提升生成图谱质量，为大模型利用结构化知识提供可扩展方案。
原文摘要 · Abstract (English)
Knowledge graphs (KGs) provide structured, verifiable grounding for large language models (LLMs), but current LLM-based systems commonly use KGs as auxiliary structures for text retrieval, leaving their intrinsic quality underexplored. In this work, we propose Wikontic, a multi-stage pipeline that constructs KGs from open-domain text by extracting candidate triplets with qualifiers, enforcing Wikidata-based type and relation constraints, and normalizing entities to reduce duplication. The resulting KGs are compact, ontology-consistent, and well-connected; on MuSiQue, the correct answer entity appears in 96% of generated triplets. On HotpotQA, our triplets-only setup achieves 76.0 F1, and on MuSiQue 59.8 F1, matching or surpassing several retrieval-augmented generation baselines that still require textual context. In addition, Wikontic attains state-of-the-art information-retention performance on the MINE-1 benchmark (86%), outperforming prior KG construction methods. Wikontic is also efficient at build time: KG construction uses less than 1,000 output tokens, about 3$\times$ fewer than AriGraph and $<$1/20 of GraphRAG. The proposed pipeline enhances the quality of the generated KG and offers a scalable solution for leveraging structured knowledge in LLMs.
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。