用大模型+本体约束，让生物医学关系提取更标准、更准确。
RELATE: Relation Extraction in Biomedical Abstracts with LLMs and Ontology Constraints
- 分三步：预处理本体、用SapBERT找相似谓词、大模型重排并处理否定句。
- 在ChemProt上精确匹配率达52%，前10名准确率94%。
- 适合做生物医学知识图谱构建的科研人员和医药数据工程师。
生物医学知识图谱对药物发现和临床决策支持至关重要，但其仍不完整。大语言模型在提取生物医学关系方面表现优异，但输出缺乏标准化且与本体不一致，限制了知识图谱的整合。我们提出RELATE，一个三阶段流水线，将大模型提取的关系映射到标准化的本体谓词，使用ChemProt和Biolink Model。流程包括：(1) 用谓词嵌入预处理本体；(2) 利用SapBERT增强的相似性检索；(3) 带显式否定处理的大模型重排序。该方法将关系提取从自由文本输出转化为结构化、本体约束的表示。在ChemProt基准上，RELATE实现52%的精确匹配率和94%的accuracy@10；在2,400份HEAL项目摘要中，有效排除无关关联（0.4%），识别否定陈述。RELATE在保证质量的同时捕捉细微生物医学关系，为知识图谱扩充提供可扩展、语义准确的框架。通过向量搜索与上下文大模型推理结合，实现了从非结构化文献到标准化知识图谱的转换。
原文摘要 · Abstract (English)
Biomedical knowledge graphs (KGs) are vital for drug discovery and clinical decision support but remain incomplete. Large language models (LLMs) excel at extracting biomedical relations, yet their outputs lack standardization and alignment with ontologies, limiting KG integration. We introduce RELATE, a three-stage pipeline that maps LLM-extracted relations to standardized ontology predicates using ChemProt and the Biolink Model. The pipeline includes: (1) ontology preprocessing with predicate embeddings, (2) similarity-based retrieval enhanced with SapBERT, and (3) LLM-based reranking with explicit negation handling. This approach transforms relation extraction from free-text outputs to structured, ontology-constrained representations. On the ChemProt benchmark, RELATE achieves 52% exact match and 94% accuracy@10, and in 2,400 HEAL Project abstracts, it effectively rejects irrelevant associations (0.4%) and identifies negated assertions. RELATE captures nuanced biomedical relationships while ensuring quality for KG augmentation. By combining vector search with contextual LLM reasoning, RELATE provides a scalable, semantically accurate framework for converting unstructured biomedical literature into standardized KGs.
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。