EMNLP Findings2025
Schema Generation for Large Knowledge Graphs Using Large Language Models
Bohui Zhang, Yuan He, Lydia Pintscher, Albert Meroño-Peñuela, Elena Simperl
Abstract
Schemas play a vital role in ensuring data quality and supporting usability in the Semantic Web and natural language processing. Traditionally, their creation demands substantial involvement from knowledge engineers and domain experts. Leveraging the impressive capabilities of large language models (LLMs) in tasks like ontology engineering, we explore schema generation using LLMs. To bridge the resource gap, we introduce two datasets: YAGO Schema and Wikidata EntitySchema, along with novel evaluation metrics. The LLMbased pipelines utilize local and global information from knowledge graphs (KGs) to generate schemas in Shape Expressions (ShEx). Experiments demonstrate LLMs' strong potential in producing high-quality ShEx schemas, paving the way for scalable, automated schema generation for large KGs. Furthermore, our benchmark introduces a new challenge for structured generation, pushing the limits of LLMs on syntactically rich formalisms.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on14
- Can Language Models Solve Graph Problems in Natural Language?Heng Wang, Shangbin Feng, Tianxing He, Zhaoxuan Tan et al.NeurIPS 2023 · 420 citations
- Deep Bidirectional Language-Knowledge Graph PretrainingMichihiro Yasunaga, Antoine Bosselut, Hongyu Ren, Xikun Zhang et al.NeurIPS 2022 · 294 citations
- Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge GraphJiashuo Sun, Chengjin Xu, Lumingyuan Tang, Saizhuo Wang et al.ICLR 2024 · 247 citations
- GraphGPT: Graph Instruction Tuning for Large Language ModelsJiabin Tang, Yuhao Yang, Wei Wei, Lei Shi et al.SIGIR 2024 · 182 citations
- GraphAdapter: Tuning Vision-Language Models With Dual Knowledge GraphXin Li, Dongze Lian, Zhihe Lu, Jiawang Bai et al.NeurIPS 2023 · 138 citations
Related papers
- Learning to Generate Structured Output with Schema Reinforcement LearningYaxi Lu, Haolun Li, Xin Cong, Zhong Zhang et al.ACL 2025 · 21 citations
- AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale CorporaJiaxin Bai, Wei Fan, Qi Hu, Qing Zong et al.ACL 2026 · 27 citations
- SCOPE and SCION: A Benchmark and an Auditable Reference Pipeline for Schema Induction and Fusion from TextMiaobo Hu, Xiaobo Guo, Shuhao Hu, BoKun Wang et al.ICML 2026
- MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language ModelsYilin Wen, Zifeng Wang, Jimeng SunACL 2024 · 74 citations
- Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph ConstructionBowen Zhang, Harold SohEMNLP 2024 · 65 citations
