Same Verdict, Different Reasons: LLM-as-a-Judge and Clinician Disagreement on Medical Chatbot Completeness

• URL: http://arxiv.org/abs/2604.16383v1
• Date: Thu, 26 Mar 2026 19:01:55 GMT
• Title: Same Verdict, Different Reasons: LLM-as-a-Judge and Clinician Disagreement on Medical Chatbot Completeness
• Abstract summary: 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.
• Score: 49.2667937337333
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLM-as-a-Judge frameworks are increasingly trusted to automate evaluation in place of human experts, yet their reliability in high-stakes medical contexts remains unproven. We stress-test this assumption for detecting incomplete patient-facing medical responses, evaluating three rubric granularities (General-Likert, Analytical-Rubric, Dynamic-Checklist) and three backbone models across two clinician-annotated datasets, including HealthBench, the largest publicly available benchmark for medical response evaluation. LLM Judges discriminate complete from incomplete responses at and slightly above near chance (AUC $0.49$--$0.66$); at the threshold required to recall $90\%$ of incomplete responses, clinicians must still review the vast majority of the dataset, offering no triage utility. Even when model and clinician verdicts agree, they rarely cite the same explanation; and when they diverge, false positives stem from over-flagging non-essential gaps while false negatives reflect outright detection failures. These results reveal that LLM Judges and clinicians apply fundamentally different completeness standards; a finding that undermines their use as autonomous evaluators or triage filters in clinical settings.

Related papers

• Clinician-Level Agreement Without Clinical Caution: LLM Evaluator Limits in Medical AI Benchmarking [27.829988205900055]
  We introduce MedQADE, the first standardised open-response clinical benchmark for German.<n>The top-performing evaluator model, Gemini 3 Flash, reached alignment consistent with the physician ceiling.<n>Despite this statistical alignment, automated evaluators exhibited near-absent clinical metacognition.
  arXiv  Detail & Related papers  (2026-07-01T15:55:31Z)
• 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)
• CLEAR: Revealing How Noise and Ambiguity Degrade Reliability in LLMs for Medicine [9.346299965194746]
  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.
  arXiv  Detail & Related papers  (2026-05-01T18:23:24Z)
• Faithful or Just Plausible? Evaluating the Faithfulness of Closed-Source LLMs in Medical Reasoning [0.0]
  We conduct a systematic evaluation of faithfulness in medical reasoning among three widely used closed-source large language models.<n>We find that CoT reasoning steps often do not causally drive predictions, and models readily incorporate external hints without acknowledgment.
  arXiv  Detail & Related papers  (2026-03-14T15:30:53Z)
• MedArena: Comparing LLMs for Medicine-in-the-Wild Clinician Preferences [50.71326426975699]
  We present MedArena, an interactive evaluation platform for medical large language models (LLMs)<n>Given a clinician-provided query, MedArena presents responses from two randomly selected models and asks the user to select the preferred response.<n>Out of 1571 preferences collected across 12 LLMs up to November 1, 2025, Gemini 2.0 Flash Thinking, Gemini 2.5 Pro, and GPT-4o were the top three models by Bradley-Terry rating.
  arXiv  Detail & Related papers  (2026-03-13T22:30:26Z)
• LiveMedBench: A Contamination-Free Medical Benchmark for LLMs with Automated Rubric Evaluation [22.211535340726073]
  LiveMedBench is a continuously updated benchmark that harvests real-world clinical cases from online medical communities.<n>LiveMedBench comprises 2,756 real-world cases spanning 38 medical specialties and multiple languages, paired with 16,702 unique evaluation criteria.<n>Extensive evaluation reveals that even the best-performing model achieves only 39.2%, and 84% of models exhibit performance degradation on post-cutoff cases.
  arXiv  Detail & Related papers  (2026-02-10T23:38:25Z)
• Uncovering Latent Bias in LLM-Based Emergency Department Triage Through Proxy Variables [2.9269181918140643]
  We investigate bias in large language models (LLMs)-based medical AI systems applied to emergency department (ED) triage.<n>Our results reveal discriminatory behavior mediated through proxy variables in ED triage scenarios.<n>These findings indicate that AI systems is still imperfectly trained on noisy, sometimes non-causal signals that do not reliably reflect true patient acuity.
  arXiv  Detail & Related papers  (2026-01-13T07:49:41Z)
• 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)
• LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation [58.25892575437433]
  evaluating large language models (LLMs) in medicine is crucial because medical applications require high accuracy with little room for error.<n>We present LLMEval-Med, a new benchmark covering five core medical areas, including 2,996 questions created from real-world electronic health records and expert-designed clinical scenarios.
  arXiv  Detail & Related papers  (2025-06-04T15:43:14Z)
• Quantifying the Reasoning Abilities of LLMs on Real-world Clinical Cases [48.87360916431396]
  We introduce MedR-Bench, a benchmarking dataset of 1,453 structured patient cases, annotated with reasoning references.<n>We propose a framework encompassing three critical examination recommendation, diagnostic decision-making, and treatment planning, simulating the entire patient care journey.<n>Using this benchmark, we evaluate five state-of-the-art reasoning LLMs, including DeepSeek-R1, OpenAI-o3-mini, and Gemini-2.0-Flash Thinking, etc.
  arXiv  Detail & Related papers  (2025-03-06T18:35:39Z)

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.