๐
๐
The Cartographer
First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows
April 20, 2026 ยท Grace Period ยท + Add venue
Authors
Sihao Xing, Zaur Gouliev
arXiv ID
2604.18038
Category
cs.CY: Computers & Society
Cross-listed
cs.AI
Citations
0
Abstract
Large language models (LLMs) are increasingly used in clinical settings, raising concerns about racial bias in both generated medical text and clinical reasoning. Existing studies have identified bias in medical LLMs, but many focus on single models and give less attention to mitigation. This study uses the EU AI Act as a governance lens to evaluate five widely used LLMs across two tasks, namely synthetic patient-case generation and differential diagnosis ranking. Using race-stratified epidemiological distributions in the United States and expert differential diagnosis lists as benchmarks, we apply structured prompt templates and a two-part evaluation design to examine implicit and explicit racial bias. All models deviated from observed racial distributions in the synthetic case generation task, with GPT-4.1 showing the smallest overall deviation. In the differential diagnosis task, DeepSeek V3 produced the strongest overall results across the reported metrics. When embedded in an agentic workflow, DeepSeek V3 showed an improvement of 0.0348 in mean p-value, 0.1166 in median p-value, and 0.0949 in mean difference relative to the standalone model, although improvement was not uniform across every metric. These findings support multi-metric bias evaluation for AI systems used in medical settings and suggest that retrieval-based agentic workflows may reduce some forms of explicit bias in benchmarked diagnostic tasks. Detailed prompt templates, experimental datasets, and code pipelines are available on our GitHub.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Computers & Society
R.I.P.
๐ป
Ghosted
Artificial Intelligence: the global landscape of ethics guidelines
R.I.P.
๐ป
Ghosted
The role of artificial intelligence in achieving the Sustainable Development Goals
R.I.P.
๐ป
Ghosted
Green AI
R.I.P.
๐ป
Ghosted
Principles alone cannot guarantee ethical AI
R.I.P.
๐ป
Ghosted