Measuring Stability Beyond Accuracy in Small Open-Source Medical Large Language Models for Pediatric Endocrinology

• URL: http://arxiv.org/abs/2601.11567v1
• Date: Fri, 26 Dec 2025 14:30:53 GMT
• Title: Measuring Stability Beyond Accuracy in Small Open-Source Medical Large Language Models for Pediatric Endocrinology
• Authors: Vanessa D'Amario, Randy Daniel, Alessandro Zanetti, Dhruv Edamadaka, Nitya Alaparthy, Joshua Tarkoff,
• Abstract summary: Small open-source medical large language models (LLMs) offer promising opportunities for low-resource deployment and broader accessibility.<n>We use coupled to human evaluation and clinical review to assess six small open-source medical LLMs.
• Score: 34.80893325510028
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Small open-source medical large language models (LLMs) offer promising opportunities for low-resource deployment and broader accessibility. However, their evaluation is often limited to accuracy on medical multiple choice question (MCQ) benchmarks, and lacks evaluation of consistency, robustness, or reasoning behavior. We use MCQ coupled to human evaluation and clinical review to assess six small open-source medical LLMs (HuatuoGPT-o1 (Chen 2024), Diabetica-7B, Diabetica-o1 (Wei 2024), Meditron3-8B (Sallinen2025), MedFound-7B (Liu 2025), and ClinicaGPT-base-zh (Wang 2023)) in pediatric endocrinology. In deterministic settings, we examine the effect of prompt variation on models' output and self-assessment bias. In stochastic settings, we evaluate output variability and investigate the relationship between consistency and correctness. HuatuoGPT-o1-8B achieved the highest performance. The results show that high consistency across the model response is not an indicator of correctness, although HuatuoGPT-o1-8B showed the highest consistency rate. When tasked with selecting correct reasoning, both HuatuoGPT-o1-8B and Diabetica-o1 exhibit self-assessment bias and dependency on the order of the candidate explanations. Expert review of incorrect reasoning rationales identified a mix of clinically acceptable responses and clinical oversight. We further show that system-level perturbations, such as differences in CUDA builds, can yield statistically significant shifts in model output despite stable accuracy. This work demonstrates that small, semantically negligible prompt perturbations lead to divergent outputs, raising concerns about reproducibility of LLM-based evaluations and highlights the output variability under different stochastic regimes, emphasizing the need of a broader diagnostic framework to understand potential pitfalls in real-world clinical decision support scenarios.

Related papers

• Prompt Sensitivity and Answer Consistency of Small Open-Source Large Language Models on Clinical Question Answering: Implications for Low-Resource Healthcare Deployment [0.0]
  Small open-source language models are gaining attention for healthcare applications in low-resource settings.<n>We evaluate five open-source models (Gemma 2 2B, Phi-3 Mini 3.8B, Llama 3.2 3B, Mistral 7B, and Meditron-7B) across three clinical question answering datasets.
  arXiv  Detail & Related papers  (2026-03-01T04:37:48Z)
• When Metrics Disagree: Automatic Similarity vs. LLM-as-a-Judge for Clinical Dialogue Evaluation [18.338933046286257]
  Large language models (LLMs) are increasingly employed to address diverse problems, including medical queries.<n>LLMs often perform poorly in medical contexts, potentially leading to harmful misguidance for users.<n>This paper focuses on fine-tuning the Llama 2 7B, a transformer-based, decoder-only model, using transcripts from real patient-doctor interactions.
  arXiv  Detail & Related papers  (2026-02-27T21:09:43Z)
• A Multi-Agent Framework for Medical AI: Leveraging Fine-Tuned GPT, LLaMA, and DeepSeek R1 for Evidence-Based and Bias-Aware Clinical Query Processing [0.4349324020366305]
  Large language models (LLMs) show promise for healthcare question answering, but clinical use is limited by weak verification, insufficient evidence grounding, and unreliable confidence signalling.<n>We propose a multi-agent medical QA framework that combines complementary LLMs with evidence retrieval, uncertainty estimation, and bias checks to improve answer reliability.
  arXiv  Detail & Related papers  (2026-02-15T14:17:27Z)
• An Explainable and Fair AI Tool for PCOS Risk Assessment: Calibration, Subgroup Equity, and Interactive Clinical Deployment [0.10026496861838446]
  This paper presents a fairness-audited and interpretable machine learning framework for predicting polycystic ovary syndrome (PCOS)<n>The framework integrated SHAP-based feature attributions with demographic audits to connect predictive explanations with observed disparities for actionable insights.<n>A Streamlit-based web interface enables real-time PCOS risk assessment, Rotterdam criteria evaluation, and interactive 'what-if' analysis.
  arXiv  Detail & Related papers  (2025-11-08T16:14:56Z)
• A Multi-faceted Analysis of Cognitive Abilities: Evaluating Prompt Methods with Large Language Models on the CONSORT Checklist [1.1731001328350983]
  This study applies a behavioral and metacognitive analytic approach using an expert-validated dataset.<n>We analyze both cognitive adaptation and calibration error using metrics: Expected Error (ECE) and a baseline-normalized Relative Error (RCE)<n>Our results reveal pronounced miscalibration and overconfidence in both models, especially under clinical role-playing conditions.
  arXiv  Detail & Related papers  (2025-10-22T00:15:02Z)
• MEDEQUALQA: Evaluating Biases in LLMs with Counterfactual Reasoning [7.167933033102407]
  We introduce MEDEQUALQA, a counterfactual benchmark that perturbs only patient pronouns while holding critical symptoms and conditions constant.<n>We evaluate a GPT-4.1 model and compute Semantic Textual Similarity (STS) between reasoning traces to measure stability across pronoun variants.<n>Our results show overall high similarity (mean STS >0.80), but reveal consistent localized divergences in cited risk factors, guideline anchors, and differential ordering.
  arXiv  Detail & Related papers  (2025-10-09T22:12:58Z)
• EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models [82.43729208063468]
  Recent benchmarks for medical Large Vision-Language Models (LVLMs) emphasize leaderboard accuracy, overlooking reliability and safety.<n>We study sycophancy -- models' tendency to uncritically echo user-provided information.<n>We introduce EchoBench, a benchmark to systematically evaluate sycophancy in medical LVLMs.
  arXiv  Detail & Related papers  (2025-09-24T14:09:55Z)
• Evaluating Large Language Models for Evidence-Based Clinical Question Answering [4.101088122511548]
  Large Language Models (LLMs) have demonstrated substantial progress in biomedical and clinical applications.<n>We curate a benchmark drawing from Cochrane systematic reviews and clinical guidelines.<n>We observe consistent performance patterns across sources and clinical domains.
  arXiv  Detail & Related papers  (2025-09-13T15:03:34Z)
• Med-RewardBench: Benchmarking Reward Models and Judges for Medical Multimodal Large Language Models [57.73472878679636]
  We introduce Med-RewardBench, the first benchmark specifically designed to evaluate medical reward models and judges.<n>Med-RewardBench features a multimodal dataset spanning 13 organ systems and 8 clinical departments, with 1,026 expert-annotated cases.<n>A rigorous three-step process ensures high-quality evaluation data across six clinically critical dimensions.
  arXiv  Detail & Related papers  (2025-08-29T08:58:39Z)
• Structured Outputs Enable General-Purpose LLMs to be Medical Experts [50.02627258858336]
  Large language models (LLMs) often struggle with open-ended medical questions.<n>We propose a novel approach utilizing structured medical reasoning.<n>Our approach achieves the highest Factuality Score of 85.8, surpassing fine-tuned models.
  arXiv  Detail & Related papers  (2025-03-05T05:24:55Z)
• Towards Reliable Medical Image Segmentation by Modeling Evidential Calibrated Uncertainty [57.023423137202485]
  Concerns regarding the reliability of medical image segmentation persist among clinicians.<n>We introduce DEviS, an easily implementable foundational model that seamlessly integrates into various medical image segmentation networks.<n>By leveraging subjective logic theory, we explicitly model probability and uncertainty for medical image segmentation.
  arXiv  Detail & Related papers  (2023-01-01T05:02:46Z)
• Hemogram Data as a Tool for Decision-making in COVID-19 Management: Applications to Resource Scarcity Scenarios [62.997667081978825]
  COVID-19 pandemics has challenged emergency response systems worldwide, with widespread reports of essential services breakdown and collapse of health care structure. This work describes a machine learning model derived from hemogram exam data performed in symptomatic patients. Proposed models can predict COVID-19 qRT-PCR results in symptomatic individuals with high accuracy, sensitivity and specificity.
  arXiv  Detail & Related papers  (2020-05-10T01:45:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.