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

Olawumi Olasunkanmi, Matthew Satusky, Hong Yi, Chris Bizon, Harlin Lee, Stanley Ahalt
Proceedings of the Fifth Machine Learning for Health Symposium, PMLR 297:1178-1193, 2026.

Abstract

Biomedical knowledge graphs ({KG}s) are vital for drug discovery and clinical decision support but remain incomplete. Large language models ({LLM}s) 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 {KG}s.

Cite this Paper

BibTeX
@InProceedings{pmlr-v297-olasunkanmi26a, title = {{RELATE}: Relation Extraction in Biomedical Abstracts with {LLM}s and Ontology Constraints}, author = {Olasunkanmi, Olawumi and Satusky, Matthew and Yi, Hong and Bizon, Chris and Lee, Harlin and Ahalt, Stanley}, booktitle = {Proceedings of the Fifth Machine Learning for Health Symposium}, pages = {1178--1193}, year = {2026}, editor = {Argaw, Peniel and Zhang, Haoran and Jabbour, Sarah and Chandak, Payal and Ji, Jerry and Mukherjee, Sumit and Salaudeen, Olawale and Chang, Trenton and Healey, Elizabeth and Gröger, Fabian and Adibi, Amin and Hegselmann, Stefan and Wild, Benjamin and Noori, Ayush}, volume = {297}, series = {Proceedings of Machine Learning Research}, month = {13--14 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v297/main/assets/olasunkanmi26a/olasunkanmi26a.pdf}, url = {https://proceedings.mlr.press/v297/olasunkanmi26a.html}, abstract = {Biomedical knowledge graphs ({KG}s) are vital for drug discovery and clinical decision support but remain incomplete. Large language models ({LLM}s) 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 {KG}s.} }
Endnote
%0 Conference Paper %T RELATE: Relation Extraction in Biomedical Abstracts with LLMs and Ontology Constraints %A Olawumi Olasunkanmi %A Matthew Satusky %A Hong Yi %A Chris Bizon %A Harlin Lee %A Stanley Ahalt %B Proceedings of the Fifth Machine Learning for Health Symposium %C Proceedings of Machine Learning Research %D 2026 %E Peniel Argaw %E Haoran Zhang %E Sarah Jabbour %E Payal Chandak %E Jerry Ji %E Sumit Mukherjee %E Olawale Salaudeen %E Trenton Chang %E Elizabeth Healey %E Fabian Gröger %E Amin Adibi %E Stefan Hegselmann %E Benjamin Wild %E Ayush Noori %F pmlr-v297-olasunkanmi26a %I PMLR %P 1178--1193 %U https://proceedings.mlr.press/v297/olasunkanmi26a.html %V 297 %X Biomedical knowledge graphs ({KG}s) are vital for drug discovery and clinical decision support but remain incomplete. Large language models ({LLM}s) 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 {KG}s.
APA
Olasunkanmi, O., Satusky, M., Yi, H., Bizon, C., Lee, H. & Ahalt, S.. (2026). RELATE: Relation Extraction in Biomedical Abstracts with LLMs and Ontology Constraints. Proceedings of the Fifth Machine Learning for Health Symposium, in Proceedings of Machine Learning Research 297:1178-1193 Available from https://proceedings.mlr.press/v297/olasunkanmi26a.html.

Related Material