Race, Ethnicity and Their Implication on Bias in Large Language Models
Hu, S.; Li, R.; Gao, Y.
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.
Similar papers in this journal
- Generating hard-to-obtain information from easy-to-obtain information: applications in drug discovery and clinical inference 93%
- Predictive coding is a consequence of energy efficiency in recurrent neural networks 93%
- Single-Cell Multi-Modal GAN (scMMGAN) reveals spatial patterns in single-cell data from triple negative breast cancer 93%
Similar papers in this journal
- Modular Clinical Decision Support Networks (MoDN)—Updatable, Interpretable, and Portable Predictions for Evolving Clinical Environments 93%
- Explainable deep learning for disease activity prediction in chronic inflammatory joint diseases 90%
- Uncovering the effects of model initialization on deep model generalization: A study with adult and pediatric chest X-ray images 90%
"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.