David Fraile Navarro

David Fraile Navarro, Berardino Como, Jialei Sheng et al.

Patient-voiced clinical-triage benchmarks report high under-triage rates for consumer LLMs for constrained multiple-choice output, yet the same cases score differently with free-text. We ask whether output format changes the model's \emph{clinical representation} or only the mapping from a preserved representation to an answer. Using sparse-autoencoder (SAE) features in Gemma 3 4B/12B IT and Qwen3-8B, we find the same medical features fire on the shared clinical narrative under both formats but go {silent} at the multiple-choice decision token in all the cases at every model. Three independent methods (natural-language autoencoder verbalization, decision-token logit attribution, and top-feature characterization) agree that scaffold and format features, but not medical features, drive the decision logits. Behaviorally, the multiple-choice penalty inverts under both structured and natural-language input, option-order shuffle rules out positional bias, and the gap is dominated by off-by-one decision (the model picks an adjacent acuity letter to the gold answer) rather than knowledge failure. Thus, the failure originates in the output format and not in the clinical representation.

David Fraile Navarro, Farah Magrabi, Enrico Coiera

Ramaswamy et al. reported in \textit{Nature Medicine} that ChatGPT Health under-triages 51.6\% of emergencies, concluding that consumer-facing AI triage poses safety risks. However, their evaluation used an exam-style protocol -- forced A/B/C/D output, knowledge suppression, and suppression of clarifying questions -- that differs fundamentally from how consumers use health chatbots. We tested five frontier LLMs (GPT-5.2, Claude Sonnet 4.6, Claude Opus 4.6, Gemini 3 Flash, Gemini 3.1 Pro) on a 17-scenario partial replication bank under constrained (exam-style, 1,275 trials) and naturalistic (patient-style messages, 850 trials) conditions, with targeted ablations and prompt-faithful checks using the authors' released prompts. Naturalistic interaction improved triage accuracy by 6.4 percentage points ($p = 0.015$). Diabetic ketoacidosis was correctly triaged in 100\% of trials across all models and conditions. Asthma triage improved from 48\% to 80\%. The forced A/B/C/D format was the dominant failure mechanism: three models scored 0--24\% with forced choice but 100\% with free text (all $p < 10^{-8}$), consistently recommending emergency care in their own words while the forced-choice format registered under-triage. Prompt-faithful checks on the authors' exact released prompts confirmed the scaffold produces model-dependent, case-dependent results. The headline under-triage rate is highly contingent on evaluation format and should not be interpreted as a stable estimate of deployed triage behavior. Valid evaluation of consumer health AI requires testing under conditions that reflect actual use.