---
title: "SynCABEL: Synthetic Contextualized Augmentation for Biomedical Entity Linking"
authors:
  - "Adam Remaki"
  - "Christel Gérardin"
  - "Eulàlia Farré-Maduell"
  - "Martin Krallinger"
  - "Xavier Tannier"
doi: "10.24963/ijcai.2026/763"
url: "https://ijcai.org/proceedings/2026/763"
pdf: "https://ijcai.org/proceedings/2026/0763.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "6859-6867"
track: "AI and Health"
keywords:
  - "Health data mining: Health data mining"
  - "Medical knowledge representation: Medical knowledge representation"
  - "LLM in medicine: LLM in medicine"
  - "EHR analysis: EHR analysis"
  - "Biomedical NLP: Biomedical NLP"
---

# SynCABEL: Synthetic Contextualized Augmentation for Biomedical Entity Linking

Adam Remaki, Christel Gérardin, Eulàlia Farré-Maduell, Martin Krallinger, Xavier Tannier

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 6859-6867. DOI: [10.24963/ijcai.2026/763](https://doi.org/10.24963/ijcai.2026/763)

## Abstract

We present SynCABEL (Synthetic Contextualized Augmentation for Biomedical Entity Linking), a framework that addresses a central bottleneck in supervised biomedical entity linking (BEL): the scarcity of expert-annotated training data. SynCABEL leverages large language models to generate context-rich synthetic training examples for all candidate concepts in a target knowledge base, providing broad supervision without manual annotation. We demonstrate that SynCABEL, when combined with decoder-only models and guided inference establish new state-of-the-art results across three widely used multilingual benchmarks: MedMentions for English, QUAERO for French, and SPACCC for Spanish. Evaluating data efficiency, we show that SynCABEL reaches the performance of full human supervision using up to 60% less annotated data, substantially reducing reliance on labor-intensive and costly expert labeling. Finally, acknowledging that standard evaluation based on exact code matching often underestimates clinically valid predictions due to ontology redundancy, we introduce an LLM-as-a-judge protocol. This analysis reveals that SynCABEL significantly improves the rate of clinically valid predictions. Our synthetic datasets, models, and code are released to support reproducibility and future research.
• HuggingFace Datasets & Models
• GitHub Repository