English

Quantifying and Mitigating Premature Closure in Frontier LLMs

Computation and Language 2026-05-15 v1 Artificial Intelligence

Abstract

Premature closure, or committing to a conclusion before sufficient information is available, is a recognized contributor to diagnostic error but remains underexamined in large language models (LLMs). We define LLM premature closure as inappropriate commitment under uncertainty: providing an answer, recommendation, or clinical guidance when the safer response would be clarification, abstention, escalation, or refusal. We evaluated five frontier LLMs across structured and open-ended medical tasks. In MedQA (n = 500) and AfriMed-QA (n = 490) questions where the correct choice had been removed, models still selected an answer at high rates, with baseline false-action rates of 55-81% and 53-82%, respectively. In open-ended evaluation, models gave inappropriate answers on an average of 30% of 861 HealthBench questions and 78% of 191 physician-authored adversarial queries. Safety-oriented prompting reduced premature closure across models, but residual failure persisted, highlighting the need to evaluate whether medical LLMs know when not to answer.

Keywords

Cite

@article{arxiv.2605.15000,
  title  = {Quantifying and Mitigating Premature Closure in Frontier LLMs},
  author = {Rebecca Handler and Suhana Bedi and Nigam Shah},
  journal= {arXiv preprint arXiv:2605.15000},
  year   = {2026}
}

Comments

14 pages, 3 figures, 1 table

R2 v1 2026-07-22T07:12:40.206Z