Preprint · 2024 · Open access

Evaluating Large Language Models for Public Health Classification and Extraction Tasks

Harris, Joshua, Timothy Laurence, Leo Loman, Fan Grayson, T. S. Nonnenmacher, Long, Harry, Loes WalsGriffith, Amy Douglas, Holly Fountain, Georgiou, Stelios, Jo L Hardstaff, Hopkins, Kathryn and 9 more

arXiv (Cornell University) · Published 23 May 2024 · DOI 10.48550/arxiv.2405.14766

Open PDFView at the publisherCite this paper

In brief

“Evaluating Large Language Models for Public Health Classification and Extraction Tasks” is a 2024 preprint by Harris, Joshua and 20 co-authors, published in arXiv (Cornell University). OpenAlex counts 31 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
31
Most cited in
2026 (17)
References
74
Authors
21

Abstract

Advances in Large Language Models (LLMs) have led to significant interest in their potential to support human experts across a range of domains, including public health. In this work we present automated evaluations of LLMs for public health tasks involving the classification and extraction of free text. We combine six externally annotated datasets with seven new internally annotated datasets to evaluate LLMs for processing text related to: health burden, epidemiological risk factors, and public health interventions. We evaluate eleven open-weight LLMs (7-123 billion parameters) across all tasks using zero-shot in-context learning. We find that Llama-3.3-70B-Instruct is the highest performing model, achieving the best results on 8/16 tasks (using micro-F1 scores). We see significant variation across tasks with all open-weight LLMs scoring below 60% micro-F1 on some challenging tasks, such as Contact Classification, while all LLMs achieve greater than 80% micro-F1 on others, such as GI Illness Classification. For a subset of 11 tasks, we also evaluate three GPT-4 and GPT-4o series models and find comparable results to Llama-3.3-70B-Instruct. Overall, based on these initial results we find promising signs that LLMs may be useful tools for public health experts to extract information from a wide variety of free text sources, and support public health surveillance, research, and interventions.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Joshua, H., Laurence, T., Loman, L., Grayson, F., Nonnenmacher, T. S., Harry, L., WalsGriffith, L., Douglas, A., Fountain, H., Stelios, G., Hardstaff, J. L., Kathryn, H., Chi, Y.-L., Kuyumdzhieva, G., Larkin, L., Collins, S., Mohammed, H. P., Finnie, T., Hounsome, L. S., . . . Riley, S. (2024). Evaluating Large Language Models for Public Health Classification and Extraction Tasks. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2405.14766

MLA 9

Joshua, Harris,, et al. “Evaluating Large Language Models for Public Health Classification and Extraction Tasks.” arXiv (Cornell University), 2024. https://doi.org/10.48550/arxiv.2405.14766.

Chicago

Joshua, Harris,, Timothy Laurence, Leo Loman, Fan Grayson, T. S. Nonnenmacher, Long, Harry, Loes WalsGriffith, et al. 2024. “Evaluating Large Language Models for Public Health Classification and Extraction Tasks.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2405.14766.

Harvard

Joshua, H. et al. (2024) ‘Evaluating Large Language Models for Public Health Classification and Extraction Tasks’, arXiv (Cornell University). doi:10.48550/arxiv.2405.14766.

IEEE

H. Joshua et al., “Evaluating Large Language Models for Public Health Classification and Extraction Tasks,” arXiv (Cornell University), 2024, doi: 10.48550/arxiv.2405.14766.

BibTeX

@misc{joshua2024evaluating,
  title     = {{Evaluating Large Language Models for Public Health Classification and Extraction Tasks}},
  author    = {Joshua, Harris, and Laurence, Timothy and Loman, Leo and Grayson, Fan and Nonnenmacher, T. S. and Harry, Long, and WalsGriffith, Loes and Douglas, Amy and Fountain, Holly and Stelios, Georgiou, and Hardstaff, Jo L and Kathryn, Hopkins, and Chi, Y-Ling and Kuyumdzhieva, Galena and Larkin, Lesley and Collins, Samuel and Mohammed, Hamish P. and Finnie, Thomas and Hounsome, Luke S. and Michael, Borowitz, and Riley, Steven},
  howpublished = {arXiv (Cornell University)},
  year      = {2024},
  doi       = {10.48550/arxiv.2405.14766},
  url       = {https://doi.org/10.48550/arxiv.2405.14766}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202433
20251111
20261717

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling

  • large language models
  • public health
  • text classification
  • information extraction
  • health burden
  • epidemiological risk factors
  • public health interventions
  • GPT-4

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Joshua, H., Laurence, T., Loman, L., Grayson, F., Nonnenmacher, T. S., Harry, L., WalsGriffith, L., Douglas, A., Fountain, H., Stelios, G., Hardstaff, J. L., Kathryn, H., Chi, Y.-L., Kuyumdzhieva, G., Larkin, L., Collins, S., Mohammed, H. P., Finnie, T., Hounsome, L. S., . . . Riley, S. (2024). Evaluating Large Language Models for Public Health Classification and Extraction Tasks. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2405.14766

How many times has this paper been cited?

31 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Harris, Joshua, Timothy Laurence, Leo Loman, Fan Grayson, T. S. Nonnenmacher, Long, Harry, Loes WalsGriffith, Amy Douglas, Holly Fountain, Georgiou, Stelios, Jo L Hardstaff, Hopkins, Kathryn and 9 more.

What is the DOI of this paper?

10.48550/arxiv.2405.14766, permanently at https://doi.org/10.48550/arxiv.2405.14766. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.