RELATE: Relation Extraction in Biomedical Abstracts with LLMs and Ontology Constraints

Olawumi Olasunkanmi, Matthew J Satusky, Hong Yi, Chris Bizon, Harlin Lee, Stan Ahalt

Keywords: Relation Extraction, Large Language Models, Ontology, Biolink Protocol, Biomedical Knowledge Graphs

TL;DR: RELATE maps LLM-extracted biomedical relations to standardized ontology predicates, enabling accurate, scalable conversion of free text into structured knowledge graphs.

Track: Proceedings

Abstract:

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 with free texts.
We introduce RELATE, a three-stage pipeline that maps LLM-extracted relations to standardized ontology predicates, e.g., 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 performs 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.

General Area: Applications and Practice

Specific Subject Areas: Causal Inference & Discovery, Evaluation Methods & Validity

Data And Code Availability: Yes

Ethics Board Approval: No

Entered Conflicts: I confirm the above

Anonymity: I confirm the above

Submission Number: 178