Improving few-shot named entity recognition for large language models using structured dynamic prompting with retrieval augmented generation
-scores by 8.8% and 6.3% in 5-shot and 10-shot settings, respectively. An ablation study on retrieval pool size demonstrated that strong performance can be achieved with relatively small number of annotated samples, reinforcing the annotation efficiency and scalability of our framework in real-world settings.
Authors
- Sudeshna Das (ORCID: https://orcid.org/0000-0002-2112-6986)
- Yuting Guo (ORCID: https://orcid.org/0000-0002-8919-0888)
- Abeed Sarker
- Yao Ge (ORCID: https://orcid.org/0000-0002-3323-7130)
Institutions
- Georgia Institute of Technology (US)
- Emory University (US)
- United States National Library of Medicine (US)
Publication Details
- Journal
- npj Artificial Intelligence
- Published
- 2026-03-31
- DOI
- https://doi.org/10.1038/s44387-025-00062-2
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Institutes of Health