Same Illness, Different Voice: Restating the Patient's Account Narrows Narrative Anchoring in Clinical Language Models
Clinical language models are evaluated on vignettes written in a clinician's voice, but patients describe the same illness in their own. We pair 1,000 MedQA cases with three retellings that carry the same audited original facts, in a clinical, a socioeconomic and a cultural voice, and evaluate 12 open models (3B to 24B, including two medical fine-tunes). Every model is less accurate when the patient speaks in a marked voice: 26% more errors, a pooled penalty of $-9.6$ accuracy points (95% CI $[-11.0, -8.2]$), with no detectable reduction at larger scale. The penalty is not explained by any retelling property we measured (length, omitted age, MedQA split, added clinical content) and persis...
| Authors | Prabhjot Singh, Pritam Deka, Vijay Chennareddy |
|---|---|
| Primary category | cs.CL |
| Published | 29 July 2026 |
| Last updated at source | 13 October 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.