Back

Race, Ethnicity and Their Implication on Bias in Large Language Models

Hu, S.; Li, R.; Gao, Y.

2026-01-05 health informatics
10.64898/2026.01.04.26343415 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 available datasets spanning toxicity-related generation and clinical narrative understanding tasks, we analyze three open-source models with a re-producible interpretability pipeline combining probing, neuron-level attribution, and targeted intervention. We find that demographic information is distributed across internal units with substantial cross-model variation. Although some units encode sensitive or stereotype-related associations from pretraining, identical demographic cues can induce qualitatively different behaviors. Interventions suppressing such neurons reduce bias but leave substantial residual effects, suggesting behavioral rather than representational change and motivating more systematic mitigation.

Matching journals

The top 8 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.