EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Leveraging large language models for rare disease named entity recognition

Nan Miles Xi, Yu Deng, Lin Wang iD

PLOS Digital Health · 12.02.2026 · 5 (2) · e0001242

DOI: 10.1371/journal.pdig.0001242 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Digital Health, online erschienen am 12.02.2026. Verfasst von Nan Miles Xi und 2 weiteren Autor:innen. Beteiligte Einrichtung: Data and Statistical Sciences, AbbVie Inc., North Chicago, Illinois, United States of America. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Named Entity Recognition (NER) in the rare disease domain poses unique challenges due to limited labeled data, semantic ambiguity between entity types, and long-tail distributions. In this study, we evaluate the capabilities of GPT-4o for rare disease NER under low-resource settings, using a range of prompt-based strategies including zero-shot prompting, few-shot in-context learning, retrieval-augmented generation (RAG), and task-level fine-tuning. We design a structured prompting framework that encodes domain-specific knowledge and disambiguation rules for four entity types. We further introduce two semantically guided few-shot example selection methods to improve in-context performance while reducing labeling effort. Experiments on the RareDis Corpus show that GPT-4o achieves competitive or superior performance compared to BioClinicalBERT, with task-level fine-tuning yielding the strongest performance among the evaluated approaches and improving upon the previously reported BioClinicalBERT baseline. Cost-performance analysis reveals that few-shot prompting delivers high returns at low token budgets. RAG provides limited overall gains but can improve recall for challenging entity types, especially signs and symptoms. An error taxonomy highlights common failure modes such as boundary drift and type confusion, suggesting opportunities for post-processing and hybrid refinement. Our results demonstrate that prompt-optimized LLMs can serve as effective, scalable alternatives to traditional supervised models in biomedical NER, particularly in rare disease applications where annotated data is scarce.

Autor:innen und Institutionen

  • Data and Statistical Sciences, AbbVie Inc., North Chicago, Illinois, United States of America.
  • Department of Statistics, Purdue University, West Lafayette, Indiana, United States of America.

ORCID-Profile: Lin Wang

Förderung

  • National Science Foundation

Zitieren

APA

Xi, N. M., Deng, Y., & Wang, L. (2026). Leveraging large language models for rare disease named entity recognition. PLOS Digital Health, 5(2), e0001242. https://doi.org/10.1371/journal.pdig.0001242

Vancouver

Xi NM, Deng Y, Wang L. Leveraging large language models for rare disease named entity recognition. PLOS Digital Health. 2026;5(2):e0001242. doi:10.1371/journal.pdig.0001242

BibTeX
@article{Xi2026,
  author = {Xi, Nan Miles and Deng, Yu and Wang, Lin},
  title = {Leveraging large language models for rare disease named entity recognition},
  journal = {PLOS Digital Health},
  year = {2026},
  volume = {5},
  number = {2},
  pages = {e0001242},
  doi = {10.1371/journal.pdig.0001242}
}
Kostenlos starten →