Papers
arxiv:2606.01204

Implicit Geographic Inference in LLM Medical Triage: Language-Driven Disparities in Emergency Recommendations

Published on May 31
Authors:

Abstract

Large language models show varying medical triage recommendations across languages despite similar symptom severity scores, with geographic inference influencing decisions more than translation quality.

We investigate whether large language models produce different medical triage recommendations for identical symptoms based solely on the language of the patient prompt. Using Gemini 3.5 Flash, we evaluate a neurological symptom profile (persistent headache, blurred vision, nausea) across six languages (English, Spanish, Chinese, Hindi, Japanese, Arabic) with 30 runs per condition (n=450 total API calls). We find that the model recommends emergency room visits at rates ranging from 0% (Japanese, Hindi) to 30% (English, Arabic), despite assigning nearly identical severity scores (7.7-8.0/10) across all languages. Adding a single sentence specifying the patient's US location increases ER recommendations by up to 76.7 percentage points for non-English prompts, while the reverse anchor (English prompt with a Tokyo location) reduces the ER rate from 30% to 6.7%. A back-translation control (Japanese to English) produces ER rates comparable to the English baseline, confirming that the disparity is not caused by translation quality but by implicit geographic inference from the input language. We release the complete dataset, experiment code, and results.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2606.01204
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2606.01204 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2606.01204 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.