用三种方法构建知识图谱，跨领域效果好。
Heterogeneous LLM Methods for Ontology Learning (Few-Shot Prompting, Ensemble Typing, and Attention-Based Taxonomies)
- 分任务用检索增强生成、零样本分类和注意力图模型
- 三项任务全登顶，无需微调，适配新领域快
- 适合做知识抽取与自动建模的研究者
我们针对 LLMs4OL 2025 挑战中的任务 A、B、C 提出完整系统，覆盖术语提取、类型标注和分类体系发现全流程。任务 A 采用检索增强生成（RAG）管道，联合提取领域术语及其类型，通过语义相似训练例提升性能，单次推理无需微调。任务 B 在少样本场景下复用 RAG 提示策略，在零样本场景下使用多嵌入模型的余弦相似度加权分类器。任务 C 将分类体系发现建模为图推断，利用类型标签嵌入，通过轻量级交叉注意力层预测 is-a 关系，近似软邻接矩阵。模块化设计在所有任务上均获官方排行榜第一名，验证了大模型架构在异构领域的可扩展性、适应性和鲁棒性。代码已开源：https://github.com/BelyaevaAlex/LLMs4OL-Challenge-Alexbek
原文摘要 · Abstract (English)
We present a comprehensive system for addressing Tasks A, B, and C of the LLMs4OL 2025 challenge, which together span the full ontology construction pipeline: term extraction, typing, and taxonomy discovery. Our approach combines retrieval-augmented prompting, zero-shot classification, and attention-based graph modeling -- each tailored to the demands of the respective task. For Task A, we jointly extract domain-specific terms and their ontological types using a retrieval-augmented generation (RAG) pipeline. Training data was reformulated into a document to terms and types correspondence, while test-time inference leverages semantically similar training examples. This single-pass method requires no model finetuning and improves overall performance through lexical augmentation Task B, which involves assigning types to given terms, is handled via a dual strategy. In the few-shot setting (for domains with labeled training data), we reuse the RAG scheme with few-shot prompting. In the zero-shot setting (for previously unseen domains), we use a zero-shot classifier that combines cosine similarity scores from multiple embedding models using confidence-based weighting. In Task C, we model taxonomy discovery as graph inference. Using embeddings of type labels, we train a lightweight cross-attention layer to predict is-a relations by approximating a soft adjacency matrix. These modular, task-specific solutions enabled us to achieve top-ranking results in the official leaderboard across all three tasks. Taken together these strategies showcase the scalability, adaptability, and robustness of LLM-based architectures for ontology learning across heterogeneous domains. Code is available at: https://github.com/BelyaevaAlex/LLMs4OL-Challenge-Alexbek
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。