Towards Sustainable Curation: Evaluation of Cost and Accuracy of AI Tools in Scaling Annotation Tasks in Curation of Biomedical Literature
Here we compare the performance and cost of four language models (GPT 4, Llama 3, Gemma 2 and Mixtral 8x7b) in the lightweight task of population group curation. Our findings provide insight into potential sustainable curation practices in the presence of limited resources.
Authors
- Ebelechukwu Nwafor (ORCID: https://orcid.org/0000-0002-5950-7231)
- Mary M. Lucas (ORCID: https://orcid.org/0000-0002-0413-7499)
- Anietie Andy (ORCID: https://orcid.org/0000-0002-7043-3042)
- Latrice Landry
Institutions
- Howard University (US)
- California University of Pennsylvania (US)
- Drexel University (US)
- Villanova University (US)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-02-18
- DOI
- https://doi.org/10.5281/zenodo.18924440
- Primary Topic
- Biomedical Text Mining and Ontologies
- Type
- article
- Field-Weighted Citation Impact
- 0.00