Healthy LLMs? Benchmarking LLM Knowledge of UK Government Public Health Information

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Harris, Joshua, Grayson, Fan, Feldman, Felix, Laurence, Timothy, Nonnenmacher, Toby, Higgins, Oliver, Loman, Leo, Patel, Selina, Finnie, Thomas, Collins, Samuel, Borowitz, Michael
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915844105175040
author Harris, Joshua
Grayson, Fan
Feldman, Felix
Laurence, Timothy
Nonnenmacher, Toby
Higgins, Oliver
Loman, Leo
Patel, Selina
Finnie, Thomas
Collins, Samuel
Borowitz, Michael
author_facet Harris, Joshua
Grayson, Fan
Feldman, Felix
Laurence, Timothy
Nonnenmacher, Toby
Higgins, Oliver
Loman, Leo
Patel, Selina
Finnie, Thomas
Collins, Samuel
Borowitz, Michael
contents As Large Language Models (LLMs) become widely accessible, a detailed understanding of their knowledge within specific domains becomes necessary for successful real world use. This is particularly critical in the domains of medicine and public health, where failure to retrieve relevant, accurate, and current information could significantly impact UK residents. However, while there are a number of LLM benchmarks in the medical domain, currently little is known about LLM knowledge within the field of public health. To address this issue, this paper introduces a new benchmark, PubHealthBench, with over 8000 questions for evaluating LLMs' Multiple Choice Question Answering (MCQA) and free form responses to public health queries. To create PubHealthBench we extract free text from 687 current UK government guidance documents and implement an automated pipeline for generating MCQA samples. Assessing 24 LLMs on PubHealthBench we find the latest proprietary LLMs (GPT-4.5, GPT-4.1 and o1) have a high degree of knowledge, achieving >90% accuracy in the MCQA setup, and outperform humans with cursory search engine use. However, in the free form setup we see lower performance with no model scoring >75%. Therefore, while there are promising signs that state of the art (SOTA) LLMs are an increasingly accurate source of public health information, additional safeguards or tools may still be needed when providing free form responses.
format Preprint
id arxiv_https___arxiv_org_abs_2505_06046
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Healthy LLMs? Benchmarking LLM Knowledge of UK Government Public Health Information
Harris, Joshua
Grayson, Fan
Feldman, Felix
Laurence, Timothy
Nonnenmacher, Toby
Higgins, Oliver
Loman, Leo
Patel, Selina
Finnie, Thomas
Collins, Samuel
Borowitz, Michael
Computation and Language
Machine Learning
68T50
As Large Language Models (LLMs) become widely accessible, a detailed understanding of their knowledge within specific domains becomes necessary for successful real world use. This is particularly critical in the domains of medicine and public health, where failure to retrieve relevant, accurate, and current information could significantly impact UK residents. However, while there are a number of LLM benchmarks in the medical domain, currently little is known about LLM knowledge within the field of public health. To address this issue, this paper introduces a new benchmark, PubHealthBench, with over 8000 questions for evaluating LLMs' Multiple Choice Question Answering (MCQA) and free form responses to public health queries. To create PubHealthBench we extract free text from 687 current UK government guidance documents and implement an automated pipeline for generating MCQA samples. Assessing 24 LLMs on PubHealthBench we find the latest proprietary LLMs (GPT-4.5, GPT-4.1 and o1) have a high degree of knowledge, achieving >90% accuracy in the MCQA setup, and outperform humans with cursory search engine use. However, in the free form setup we see lower performance with no model scoring >75%. Therefore, while there are promising signs that state of the art (SOTA) LLMs are an increasingly accurate source of public health information, additional safeguards or tools may still be needed when providing free form responses.
title Healthy LLMs? Benchmarking LLM Knowledge of UK Government Public Health Information
topic Computation and Language
Machine Learning
68T50
url https://arxiv.org/abs/2505.06046