Back

Beyond the hype: large language models propagate race-based medicine

Omiye, J. A.; Lester, J.; Spichak, S.; Rotemberg, V.; Daneshjou, R.

2023-07-05 health informatics
10.1101/2023.07.03.23292192 medRxiv
Show abstract

ImportanceLarge language models (LLMs) are being integrated into healthcare systems; but these models recapitulate harmful, race-based medicine. ObjectiveThe objective of this study is to assess whether four commercially available large language models (LLMs) propagate harmful, inaccurate, race-based content when responding to eight different scenarios that historically included race-based medicine or widespread misconceptions around race. Evidence ReviewQuestions were derived from discussion among 4 physician experts and prior work on race-based medical misconceptions of medical trainees. FindingsWe assessed four large language models with eight different questions that were interrogated five times each with a total of forty responses per a model. All models had examples of perpetuating race-based medicine in their responses. Models were not always consistent in their responses when asked the same question repeatedly. Conclusions and RelevanceLLMs are being proposed for use in the healthcare setting, with some models already connecting to electronic health record systems. However, this study shows that based on our findings, these LLMs could potentially cause harm by perpetuating debunked, racist concepts.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.