Papers by Michelle Kim
Race, Gender, and Age Biases in Biomedical Masked Language Models (2023.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models can be used to identify and eliminate healthcare disparities. |
| Approach: | They examine social biases present in biomedical masked language models . they curate prompts based on evidence-based practice and compare generated diagnoses . |
| Outcome: | The proposed models are less biased than BERT in gender, while the opposite is true for race and age. |