CLEAR: Revealing How Noise and Ambiguity Degrade Reliability in LLMs for Medicine

• URL: http://arxiv.org/abs/2605.01011v1
• Date: Fri, 01 May 2026 18:23:24 GMT
• Title: CLEAR: Revealing How Noise and Ambiguity Degrade Reliability in LLMs for Medicine
• Abstract summary: We introduce the CLinical Evaluation of Ambiguity and Reliability (CLEAR) framework.<n>CLEAR perturbs the number of plausible answer options, the presence of a ground truth or abstention option, and the semantic framing of answer options.<n>Applying CLEAR on three benchmarks evaluated across 17 medical large language models reveals three notable limitations.
• Score: 9.346299965194746
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Medical large language model (LLM) evaluations rely on simplified, exam-style benchmarks that rarely reflect the ambiguity of real-world medical inquiries. We introduce the CLinical Evaluation of Ambiguity and Reliability (CLEAR) framework, which assesses how decision-space presentation, ambiguity, and uncertainty affect LLMs' reasoning on medical benchmarks. CLEAR systematically perturbs (1) the number of plausible answer options, (2) the presence of a ground truth or abstention option, and (3) the semantic framing of answer options. Applying CLEAR on three benchmarks evaluated across 17 LLMs reveals three notable limitations of existing evaluation methods. First, increasing the number of plausible answers degrades a model's ability to identify the correct answer and abstain against incorrect ones. Second, this lack of caution intensifies as the framing of abstention shifts from assertive rejection like "None of the Above" to uncertainty admission like "I don't know" (IDK). Notably, just including IDK in the answer space increases incorrect answer selections. Lastly, we formalize the performance gap between identifying the correct answer and abstaining from incorrect ones as the humility deficit, which worsens with model scale. Our findings reveal limitations in standard medical benchmarks and underscore that scaling alone does not resolve LLM reliability issues.

Related papers

• 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)
• Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction [72.89352076103889]
  Large language models (LLMs) achieve high accuracy in medical diagnosis when all clinical information is provided in a single turn.<n>We introduce MINT, a high-fidelity, multi-turn medical diagnosis benchmark comprising 1,035 cases.<n>We uncover three persistent behavioral patterns that significantly impact diagnostic decisions.
  arXiv  Detail & Related papers  (2026-04-06T00:23:10Z)
• I-CALM: Incentivizing Confidence-Aware Abstention for LLM Hallucination Mitigation [2.688126466709795]
  Large language models (LLMs) frequently produce confident but incorrect answers.<n>We study whether prompt-only interventions can reduce hallucination risk without modifying the model.<n>Results show the framework can improve selective answering on factual questions without retraining.
  arXiv  Detail & Related papers  (2026-04-05T00:15:41Z)
• Same Verdict, Different Reasons: LLM-as-a-Judge and Clinician Disagreement on Medical Chatbot Completeness [49.2667937337333]
  We stress-test this assumption for detecting incomplete patient-facing medical responses.<n>We evaluate three granularities (General-Likert, Analytical-Rubric, Dynamic-Checklist) and three backbone models across two clinician-annotated datasets.
  arXiv  Detail & Related papers  (2026-03-26T19:01:55Z)
• HALF: Harm-Aware LLM Fairness Evaluation Aligned with Deployment [52.374772443536045]
  HALF (Harm-Aware LLM Fairness) is a framework that assesses model bias in realistic applications and weighs the outcomes by harm severity.<n>We show that HALF exposes a clear gap between previous benchmarking success and deployment readiness.
  arXiv  Detail & Related papers  (2025-10-14T07:13:26Z)
• SURE-Med: Systematic Uncertainty Reduction for Enhanced Reliability in Medical Report Generation [2.2185034594788164]
  We propose SURE-Med, a unified framework that systematically reduces uncertainty across three critical dimensions: visual, distributional, and contextual.<n>To mitigate visual uncertainty, a Frontal-Aware View Repair Resampling module corrects view annotation errors and adaptively selects informative features from supplementary views.<n>To tackle label distribution uncertainty, we introduce a Token Sensitive Learning objective that enhances the modeling of critical diagnostic sentences.<n>To reduce contextual uncertainty, our Contextual Evidence Filter validates and selectively incorporates prior information that aligns with the current image, effectively suppressing hallucinations.
  arXiv  Detail & Related papers  (2025-08-03T09:52:30Z)
• AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions [32.871820908561936]
  AbstentionBench is a benchmark for holistically evaluating abstention across 20 diverse datasets.<n>We find that reasoning fine-tuning degrades abstention even for math and science domains.
  arXiv  Detail & Related papers  (2025-06-10T17:57:30Z)
• Fact or Guesswork? Evaluating Large Language Models' Medical Knowledge with Structured One-Hop Judgments [108.55277188617035]
  Large language models (LLMs) have been widely adopted in various downstream task domains, but their abilities to directly recall and apply factual medical knowledge remains under-explored.<n>We introduce the Medical Knowledge Judgment dataset (MKJ), a dataset derived from the Unified Medical Language System (UMLS), a comprehensive repository of standardized vocabularies and knowledge graphs.<n>Through a binary classification framework, MKJ evaluates LLMs' grasp of fundamental medical facts by having them assess the validity of concise, one-hop statements.
  arXiv  Detail & Related papers  (2025-02-20T05:27:51Z)
• Automatic Evaluation of Healthcare LLMs Beyond Question-Answering [0.42131793931438133]
  We explore correlations between open and close benchmarks and metrics.<n>As an updated sanity check, we release a new medical benchmark--CareQA-- with both open and closed variants.<n>We propose a novel metric for open-ended evaluations --Relaxed Perplexity-- to mitigate the identified limitations.
  arXiv  Detail & Related papers  (2025-02-10T16:52:39Z)
• Uncertainty Estimation of Large Language Models in Medical Question Answering [60.72223137560633]
  Large Language Models (LLMs) show promise for natural language generation in healthcare, but risk hallucinating factually incorrect information. We benchmark popular uncertainty estimation (UE) methods with different model sizes on medical question-answering datasets. Our results show that current approaches generally perform poorly in this domain, highlighting the challenge of UE for medical applications.
  arXiv  Detail & Related papers  (2024-07-11T16:51:33Z)
• Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations [63.330182403615886]
  A major barrier towards the practical deployment of large language models (LLMs) is their lack of reliability. Three situations where this is particularly apparent are correctness, hallucinations when given unanswerable questions, and safety. In all three cases, models should ideally abstain from responding, much like humans, whose ability to understand uncertainty makes us refrain from answering questions we don't know.
  arXiv  Detail & Related papers  (2024-04-16T23:56:38Z)

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.