Published • loading... • Updated
85% Racial Bias, 61% Gender Bias: ChatGPT and DeepSeek Still Fail to Eliminate Stereotypes in Medicine
Summary by Science-Et-vie.com
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.1 Articles
1 Articles
In Adelaide, Joshua Docking's team at Flinders University showed, in work published on May 28, 2026 in the Journal of Medical Internet Research, that two models of reasoning distorted the demographic representation of common diseases, so these fictitious patients did not follow the frequencies observed in the American population, even when the instructions specified this geographical framework. The biases of the AI thus resisted the increased lo…
Coverage Details
Total News Sources1
Leaning Left0Leaning Right0Center0Last UpdatedBias DistributionNo sources with tracked biases.
Bias Distribution
- There is no tracked Bias information for the sources covering this story.
Factuality
To view factuality data please Upgrade to Premium
