# Quantifying and Mitigating Premature Closure in Frontier LLMs

arXiv: https://arxiv.org/abs/2605.15000 · HTML: https://mlsanity.com/paper/2605.15000/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 36 references that are in the map.
- First posted on arXiv 14 May 2026.

## Builds on (most cited first, 17 of 17)

- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [HealthBench: Evaluating Large Language Models Towards Improved Human Health](https://mlsanity.com/paper/2505.08775/) (2025)
- [Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration](https://mlsanity.com/paper/2402.00367/) (2024)
- [AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions](https://mlsanity.com/paper/2506.09038/) (2025)
- [The Art of Saying No: Contextual Noncompliance in Language Models](https://mlsanity.com/paper/2407.12043/) (2024)
- [Diagnostic Reasoning Prompts Reveal the Potential for Large Language Model Interpretability in Medicine](https://mlsanity.com/paper/2308.06834/) (2023)
- [Superhuman performance of a large language model on the reasoning tasks of a physician](https://mlsanity.com/paper/2412.10849/) (2024)
- [Evaluating language models as risk scores](https://mlsanity.com/paper/2407.14614/) (2024)
- [AfriMed-QA: A Pan-African, Multi-Specialty, Medical Question-Answering Benchmark Dataset](https://mlsanity.com/paper/2411.15640/) (2024)
- [HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats](https://mlsanity.com/paper/2604.27470/) (2026)
- [Large language models provide unsafe answers to patient-posed medical questions](https://mlsanity.com/paper/2507.18905/) (2025)
- [Prompt engineering paradigms for medical applications: scoping review and recommendations for better practices](https://mlsanity.com/paper/2405.01249/) (2024)
- [Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy](https://mlsanity.com/paper/2510.08646/) (2025)
- [AI Alignment Breaks at the Edge](https://mlsanity.com/paper/2602.20042/) (2026)
- [Prompt engineering does not universally improve Large Language Model performance across clinical decision-making tasks](https://mlsanity.com/paper/2512.22966/) (2025)

## Built on by (most cited first, 4 of 4)

- [InsufficiencyBench: Evaluating LLM legal advice on underspecified user queries](https://mlsanity.com/paper/2608.20220/) (2026)
- [Why Didn't It Check? Unsupported Final Claims and Their Repair in Two Tool-Equipped Language Models](https://mlsanity.com/paper/2608.27768/) (2026)
- [Can LLMs Value the Right Evidence? Evidence-Value Misalignment in Dynamic Medical Diagnosis](https://mlsanity.com/paper/2609.35627/) (2026)
- [Not Until the Evidence Says So: Teaching LLM Investigators When to Close a Case](https://mlsanity.com/paper/2610.03190/) (2026)

## Abstract (arXiv)

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.