Stability-Aware Prompt Optimization for Clinical Data Abstraction

• URL: http://arxiv.org/abs/2601.22373v1
• Date: Thu, 29 Jan 2026 22:30:35 GMT
• Title: Stability-Aware Prompt Optimization for Clinical Data Abstraction
• Abstract summary: Large language models used for clinical abstraction are sensitive to prompt wording.<n>We measure prompt sensitivity via flip rates and relate it to calibration and selective prediction.<n>We propose a dual-objective prompt optimization loop that jointly targets accuracy and stability.
• Score: 0.6401581119643504
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models used for clinical abstraction are sensitive to prompt wording, yet most work treats prompts as fixed and studies uncertainty in isolation. We argue these should be treated jointly. Across two clinical tasks (MedAlign applicability/correctness and MS subtype abstraction) and multiple open and proprietary models, we measure prompt sensitivity via flip rates and relate it to calibration and selective prediction. We find that higher accuracy does not guarantee prompt stability, and that models can appear well-calibrated yet remain fragile to paraphrases. We propose a dual-objective prompt optimization loop that jointly targets accuracy and stability, showing that explicitly including a stability term reduces flip rates across tasks and models, sometimes at modest accuracy cost. Our results suggest prompt sensitivity should be an explicit objective when validating clinical LLM systems.

Related papers

• When Confidence Fails: Overconfidence in LLMs under Uncertainty and Missing Clinical Information [14.659028787864996]
  Large Language Models (LLMs) have achieved strong performance in medical question answering and clinical reasoning tasks.<n>We conduct a behavioral analysis of LLMs under clinical information uncertainty.<n>We observe significant variation across models in their ability to abstain when the correct answer is unavailable.
  arXiv  Detail & Related papers  (2026-08-10T03:28:46Z)
• Evaluating the Diagnostic Robustness of Vision-Language Models Under Visual and Textual Perturbations [3.765860543344957]
  We assess the diagnostic robustness of four VLM families under evidence-preserving perturbations.<n>Our results reveal significant vulnerabilities in presentation-order stability, with models exhibiting prediction flips in up to 48.9% of cases.
  arXiv  Detail & Related papers  (2026-08-05T14:09:55Z)
• Beyond Scalar Scores: Exploring LLM-based Metrics for Clinical Significance Evaluation in Radiology Reports [49.5225801722164]
  Existing metrics obscure this requirement by reducing report quality to a medically ungrounded scalar.<n>We study this boundary using ReEvalMed benchmark as testbed and evaluate metric-level clinical significance.
  arXiv  Detail & Related papers  (2026-06-17T08:10:30Z)
• Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs [53.697403481143404]
  Large Vision-Language Models (LVLMs) have achieved strong performance across medical imaging tasks.<n>But they remain prone to factual inconsistencies, poor visual grounding, and misalignment with clinically meaningful feedback.
  arXiv  Detail & Related papers  (2026-06-10T18:35:36Z)
• When Large Language Models Fail in Healthcare: Evaluating Sensitivity to Prompt Variations [1.0152838128195467]
  Large Language Models (LLMs) are increasingly used in healthcare for tasks such as clinical question answering, diagnosis support, and report summarization.<n>Despite their promise, these models remain highly sensitive to subtle prompt perturbations, both lexical and syntactic, posing serious risks in safety-critical clinical applications.<n>We categorize perturbations into natural and adversarial types and examine their effect on model consistency, accuracy, and reliability in clinical reasoning tasks.
  arXiv  Detail & Related papers  (2026-06-05T13:07:11Z)
• Same Patient, Different Words, Different Diagnosis? Evaluating Semantic Stability in Clinical LLMs [5.580559622582594]
  We introduce three metrics to quantify model sensitivity: MeaningPreserving Variation Sensitivity (MVS), confidence variation (C), and Worst-Case Instability (WCI)<n>Our results demonstrate that differences between domain-specific (DS) models are mixed and highly model-dependent, i.e., domain specialization does not consistently improve or reduce robustness to meaning-preserving prompt reformulations.
  arXiv  Detail & Related papers  (2026-05-28T23:03:43Z)
• Uncertainty-Aware Exploratory Direct Preference Optimization for Multimodal Large Language Models [53.15468578562038]
  We propose an Uncertainty-aware Exploratory Direct Preference Optimization (UE-DPO) method for Multimodal Large Language Models (MLLMs)<n>We first quantify the uncertainty from the model's failure to ground token predictions in the given image.<n>We then encourage more learning pressure on visually deficient tokens in preferred samples, and alleviate the over-penalization of beneficial knowledge in dispreferred samples.
  arXiv  Detail & Related papers  (2026-05-06T13:08:12Z)
• Beyond Prompt: Fine-grained Simulation of Cognitively Impaired Standardized Patients via Stochastic Steering [58.85421622061983]
  We propose StsPatient for the fine-grained simulation of cognitively impaired patients.<n>We capture domain-specific features by extracting steering vectors from contrastive pairs of instructions and responses.<n>StsPatient significantly outperforms baselines in both clinical authenticity and severity controllability.
  arXiv  Detail & Related papers  (2026-04-14T02:37:46Z)
• Calibrated Bayesian Deep Learning for Explainable Decision Support Systems Based on Medical Imaging [6.826979426009301]
  It is imperative that models quantify uncertainty in a manner that correlates with prediction correctness, allowing clinicians to identify unreliable outputs for further review.<n>The present paper proposes a generalizable probabilistic optimization framework grounded in Bayesian deep learning.<n>Specifically, a novel Confidence-Uncertainty Boundary Loss (CUB-Loss) is introduced that imposes penalties on high-certainty errors and low-certainty correct predictions.<n>The proposed framework is validated on three distinct medical imaging tasks: automatic screening of pneumonia, diabetic retinopathy detection, and identification of skin lesions.
  arXiv  Detail & Related papers  (2026-02-12T14:03:41Z)
• Intervention Efficiency and Perturbation Validation Framework: Capacity-Aware and Robust Clinical Model Selection under the Rashomon Effect [8.16102315566872]
  coexistence of multiple models with comparable performance poses fundamental challenges for trustworthy deployment and evaluation.<n>We propose two complementary tools for robust model assessment and selection: Intervention Efficiency (IE) and the Perturbation Validation Framework (PVF)<n>IE is a capacity-aware metric that quantifies how efficiently a model identifies actionable true positives when only limited interventions are feasible.<n>PVF introduces a structured approach to assess the stability of models under data perturbations, identifying models whose performance remains most invariant across noisy or shifted validation sets.
  arXiv  Detail & Related papers  (2025-11-18T10:21:07Z)
• Reasoning's Razor: Reasoning Improves Accuracy but Can Hurt Recall at Critical Operating Points in Safety and Hallucination Detection [21.190105743961798]
  Reasoning has become a central paradigm for large language models (LLMs)<n>We present the first systematic study of reasoning for classification tasks under strict low false positive rate regimes.<n>Our results reveal a clear trade-off: Think On (reasoning-augmented) generation improves overall accuracy, but underperforms at the low-FPR thresholds essential for practical use.
  arXiv  Detail & Related papers  (2025-10-23T23:23:36Z)
• Timely Clinical Diagnosis through Active Test Selection [49.091903570068155]
  We propose ACTMED (Adaptive Clinical Test selection via Model-based Experimental Design) to better emulate real-world diagnostic reasoning.<n>LLMs act as flexible simulators, generating plausible patient state distributions and supporting belief updates without requiring structured, task-specific training data.<n>We evaluate ACTMED on real-world datasets and show it can optimize test selection to improve diagnostic accuracy, interpretability, and resource use.
  arXiv  Detail & Related papers  (2025-10-21T18:10:45Z)
• Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift [12.373281238541296]
  Medical vision-language models (VLMs) offer promise for clinical decision support, yet their reliability under distribution shifts remains a major concern for safe deployment.<n>We propose DRiFt, a structured feature decoupling framework that explicitly separates clinically relevant signals from task-agnostic noise.<n>Our approach improves in-distribution performance by +11.4% Top-1 accuracy and +3.3% Macro-F1 over prior prompt-based methods.
  arXiv  Detail & Related papers  (2025-09-11T12:26:57Z)
• Beyond Benchmarks: Dynamic, Automatic And Systematic Red-Teaming Agents For Trustworthy Medical Language Models [87.66870367661342]
  Large language models (LLMs) are used in AI applications in healthcare.<n>Red-teaming framework that continuously stress-test LLMs can reveal significant weaknesses in four safety-critical domains.<n>A suite of adversarial agents is applied to autonomously mutate test cases, identify/evolve unsafe-triggering strategies, and evaluate responses.<n>Our framework delivers an evolvable, scalable, and reliable safeguard for the next generation of medical AI.
  arXiv  Detail & Related papers  (2025-07-30T08:44:22Z)
• Embeddings to Diagnosis: Latent Fragility under Agentic Perturbations in Clinical LLMs [0.0]
  We propose a geometry-aware evaluation framework, LAPD (Latent Agentic Perturbation Diagnostics), which probes the latent robustness of clinical LLMs under structured adversarial edits.<n>Within this framework, we introduce Latent Diagnosis Flip Rate (LDFR), a model-agnostic diagnostic signal that captures representational instability when embeddings cross decision boundaries in PCA-reduced latent space.<n>Our results reveal a persistent gap between surface robustness and semantic stability, underscoring the importance of geometry-aware auditing in safety-critical clinical AI.
  arXiv  Detail & Related papers  (2025-07-27T16:48:53Z)
• ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs [72.13489820420726]
  ProSA is a framework designed to evaluate and comprehend prompt sensitivity in large language models. Our study uncovers that prompt sensitivity fluctuates across datasets and models, with larger models exhibiting enhanced robustness.
  arXiv  Detail & Related papers  (2024-10-16T09:38:13Z)
• TREEMENT: Interpretable Patient-Trial Matching via Personalized Dynamic Tree-Based Memory Network [54.332862955411656]
  Clinical trials are critical for drug development but often suffer from expensive and inefficient patient recruitment. In recent years, machine learning models have been proposed for speeding up patient recruitment via automatically matching patients with clinical trials. We introduce a dynamic tree-based memory network model named TREEMENT to provide accurate and interpretable patient trial matching.
  arXiv  Detail & Related papers  (2023-07-19T12:35:09Z)
• SPeC: A Soft Prompt-Based Calibration on Performance Variability of Large Language Model in Clinical Notes Summarization [50.01382938451978]
  We introduce a model-agnostic pipeline that employs soft prompts to diminish variance while preserving the advantages of prompt-based summarization. Experimental findings indicate that our method not only bolsters performance but also effectively curbs variance for various language models.
  arXiv  Detail & Related papers  (2023-03-23T04:47:46Z)
• 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)

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.