Back
Top 5%
17.4%
Top 0.4%
10.8%
Top 2%
9.2%
Top 3%
6.3%
Top 3%
6.3%
Top 19%
5.8%
Top 4%
5.5%
Top 4%
4.1%
Top 5%
3.8%
Top 87%
3.8%
Top 4%
1.9%
Top 0.1%
1.9%
Top 4%
1.9%
Top 4%
1.5%
Top 3%
1.5%
Top 0.7%
1.5%
Top 10%
1.2%
Top 11%
1.1%
Top 24%
0.9%
Top 5%
0.9%
Top 7%
0.9%
Top 4%
0.7%
Race, Ethnicity and Their Implication on Bias in Large Language Models
2026-01-05
health informatics
Title + abstract only
View on medRxiv
Show abstract
Large language models (LLMs) increasingly operate in high-stakes settings including healthcare and medicine, where demographic attributes such as race and ethnicity may be explicitly stated or implicitly inferred from text. However, existing studies primarily document outcome-level disparities, offering limited insight into internal mechanisms underlying these effects. We present a mechanistic study of how race and ethnicity are represented and operationalized within LLMs. Using two publicly ava...
Predicted journal destinations
1
Scientific Reports
701 training papers
2
Journal of Biomedical Informatics
37 training papers
3
Journal of the American Medical Informatics Association
53 training papers
4
npj Digital Medicine
85 training papers
5
PLOS Digital Health
88 training papers
6
Nature Communications
483 training papers
7
JAMIA Open
35 training papers
8
BMC Medical Informatics and Decision Making
36 training papers
9
Journal of Medical Internet Research
81 training papers
10
PLOS ONE
1737 training papers
11
Computers in Biology and Medicine
39 training papers
12
Patterns
15 training papers
13
International Journal of Medical Informatics
25 training papers
14
JMIR Medical Informatics
16 training papers
15
BMC Medical Research Methodology
41 training papers
16
Frontiers in Digital Health
18 training papers
17
Nature Medicine
88 training papers
18
PLOS Computational Biology
141 training papers
19
JAMA Network Open
125 training papers
20
Communications Medicine
63 training papers
21
Frontiers in Psychiatry
56 training papers
22
Frontiers in Aging Neuroscience
22 training papers