Evaluating Large Language Models for Public Health Classification and Extraction Tasks

no code implementations • 23 May 2024 • Joshua Harris, Timothy Laurence, Leo Loman, Fan Grayson, Toby Nonnenmacher, Harry Long, Loes WalsGriffith, Amy Douglas, Holly Fountain, Stelios Georgiou, Jo Hardstaff, Kathryn Hopkins, Y-Ling Chi, Galena Kuyumdzhieva, Lesley Larkin, Samuel Collins, Hamish Mohammed, Thomas Finnie, Luke Hounsome, Steven Riley

For a subset of 12 tasks, we also evaluate GPT-4 and find comparable results to Llama-3-70B-Instruct, which scores equally or outperforms GPT-4 on 6 of the 12 tasks.

In-Context Learning

Shut and re-open: the role of schools in the spread of COVID-19 in Europe

no code implementations • 25 Jun 2020 • Helena B. Stage, Joseph Shingleton, Sanmitra Ghosh, Francesca Scarabel, Lorenzo Pellis, Thomas Finnie

By comparing the growth rates in daily hospitalisations or confirmed cases under different interventions, we provide evidence that the effect of school closure is visible as a reduction in the growth rate approximately 9 days after implementation.