Profile-associated financial and access-related framing in LLM-generated pediatric asthma referral plans: a factorial audit of seven large language models.
Address signal more than doubled financial-access language in AI-generated asthma referral plans.
Profile-associated financial and access-related framing in LLM-generated pediatric asthma referral plans: a factorial audit of seven large language models.
Large language models (large language models) are increasingly considered for clinical documentation, referral support, and patient-facing communication.
To evaluate whether onomastic and bundled geographic-access signals are associated with differences in large language models-generated pediatric asthma referral plans.
We conducted a cross-sectional 2 × 2 factorial audit of seven commercial large language models.
geography-linked cues more than doubled mentions of cost or insurance access
The name-signal association was directionally similar but less precise in model-profile aggregated sensitivity analysis.
The interaction term was below 1.0 (IRR, 0.79; 95% CI, 0.63-1.00; p = 0.048), indicating no positive multiplicative synergy.
Institutional Specificity and Triage Ranking were at ceiling.
SDOH Recognition Depth, Location-Friction Acknowledgment, Navigator Recommendation, and Empathy/Subjectivity differed by profile, whereas Access Priority remained low and non-significant after correction.
Large language models-generated pediatric asthma referral plans varied in financial-access, geographic-access, navigation, SDOH-recognition, and selected tone-related framing.
These findings do not establish discriminatory intent, clinical equivalence, downstream harm, or positive synergistic interaction, but support evaluating structural and access-related framing alongside biomedical content in clinical large language models audits.