Evaluating gender bias in Large Language Models in long-term care

Rickman, Samuel ORCID: 0000-0003-1921-5258 (2025) Evaluating gender bias in Large Language Models in long-term care. BMC Medical Informatics and Decision Making. ISSN 1472-6947 (In Press)

	Text (evaluating-gender-bias) - Accepted Version Pending embargo until 1 January 2100. Download (487kB)
	Text (supplementary-information) - Accepted Version Pending embargo until 1 January 2100. Download (3MB)

Abstract

Background: Large language models (LLMs) are being used to reduce the administrative burden in long-term care by automatically generating and summarising case notes. However, LLMs can reproduce bias in their training data. This study evaluates gender bias in summaries of long-term care records generated with two state-of-the-art, open-source LLMs released in 2024: Meta's Llama 3 and Google Gemma. Methods: Gender-swapped versions were created of long-term care records for 617 older people from a London local authority. Summaries of male and female versions were generated with Llama 3 and Gemma, as well as benchmark models from Meta and Google released in 2019: T5 and BART. Counterfactual bias was quantified through sentiment analysis alongside an evaluation of word frequency and thematic patterns. Results: The benchmark models exhibited some variation in output on the basis of gender. Llama 3 showed no gender-based differences across any metrics. Gemma displayed the most significant gender-based differences. Male summaries focus more on physical and mental health issues. Language used for men was more direct, with women's needs downplayed more often than men's. Conclusions: Care services are allocated on the basis of need. If women's health issues are underemphasised, this may lead to gender-based disparities in service receipt. LLMs may offer substantial benefits in easing administrative burden. However, the findings highlight the variation in state-of-the-art LLMs, and the need for evaluation of bias. The methods in this paper provide a practical framework for quantitative evaluation of gender bias in LLMs. The code is available on GitHub.

Item Type:	Article
Additional Information:	© 2025 The Author(s)
Divisions:	Care Policy and Evaluation Centre
Subjects:	R Medicine > RA Public aspects of medicine > RA0421 Public health. Hygiene. Preventive Medicine H Social Sciences
Date Deposited:	17 Jul 2025 10:54
Last Modified:	17 Jul 2025 10:54
URI:	http://eprints.lse.ac.uk/id/eprint/128867

Actions (login required)

View Item