Beyond Literal Summarization: Redefining Hallucination for Medical SOAP Note Evaluation

• URL: http://arxiv.org/abs/2604.14829v1
• Date: Thu, 16 Apr 2026 10:04:14 GMT
• Title: Beyond Literal Summarization: Redefining Hallucination for Medical SOAP Note Evaluation
• Abstract summary: We show that evaluation methods rely on lexical faithfulness, often labeling any information not explicitly present in the transcript as hallucination.<n>We show that such approaches systematically misclassify clinically valid outputs as errors, inflating hallucination rates and distorting model assessment.
• Score: 0.6533091401094101
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Evaluating large language models (LLMs) for clinical documentation tasks such as SOAP note generation remains challenging. Unlike standard summarization, these tasks require clinical abstraction, normalization of colloquial language, and medically grounded inference. However, prevailing evaluation methods including automated metrics and LLM as judge frameworks rely on lexical faithfulness, often labeling any information not explicitly present in the transcript as hallucination. We show that such approaches systematically misclassify clinically valid outputs as errors, inflating hallucination rates and distorting model assessment. Our analysis reveals that many flagged hallucinations correspond to legitimate clinical transformations, including synonym mapping, abstraction of examination findings, diagnostic inference, and guideline consistent care planning. By aligning evaluation criteria with clinical reasoning through calibrated prompting and retrieval grounded in medical ontologies we observe a significant shift in outcomes. Under a lexical evaluation regime, the mean hallucination rate is 35%, heavily penalizing valid reasoning. With inference aware evaluation, this drops to 9%, with remaining cases reflecting genuine safety concerns. These findings suggest that current evaluation practices over penalize valid clinical reasoning and may measure artifacts of evaluation design rather than true errors, underscoring the need for clinically informed evaluation in high context domains like medicine.

Related papers

• When Rubrics Fail: Hallucinations Reveal Blind Spots in Medical AI Evaluation [16.557035598746182]
  More specific rubrics better distinguish correct from hallucinated responses.<n>We develop a taxonomy of medical hallucination types and a clinician-validated error-injection pipeline.<n>We find that rubrics are most effective when explicitly checking facts, and are less effective for additional or unexpected errors they do not anticipate.
  arXiv  Detail & Related papers  (2026-09-11T11:15:46Z)
• 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)
• Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning [8.322191814123315]
  Hallucinations in medical large language models pose serious risks for clinical decision support.<n>We introduce Med-HEAL, a framework for systematically identifying, analyzing, and mitigating hallucinations in medical LLMs.
  arXiv  Detail & Related papers  (2026-05-31T15:43:42Z)
• 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)
• Toward Guarantees for Clinical Reasoning in Vision Language Models via Formal Verification [12.60121003165514]
  Vision-language models (VLMs) show promise in drafting radiology reports, yet they frequently suffer from logical inconsistencies.<n>Standard lexical metrics heavily penalize clinical paraphrasing and fail to capture these deductive failures.<n>We introduce a neurosymbolic verification framework that deterministically audits the internal consistency of VLM-generated reports.
  arXiv  Detail & Related papers  (2026-02-27T15:49:59Z)
• Beyond Accuracy: Risk-Sensitive Evaluation of Hallucinated Medical Advice [0.1609950046042424]
  We propose a risk-sensitive evaluation framework that quantifies hallucinations through the presence of risk-bearing language.<n>We apply this framework to three instruction-tuned language models using controlled patient-facing prompts designed as safety stress tests.
  arXiv  Detail & Related papers  (2026-02-07T02:25:44Z)
• AgentsEval: Clinically Faithful Evaluation of Medical Imaging Reports via Multi-Agent Reasoning [73.50200033931148]
  We introduce AgentsEval, a multi-agent stream reasoning framework that emulates the collaborative diagnostic workflow of radiologists.<n>By dividing the evaluation process into interpretable steps including criteria definition, evidence extraction, alignment, and consistency scoring, AgentsEval provides explicit reasoning traces and structured clinical feedback.<n> Experimental results demonstrate that AgentsEval delivers clinically aligned, semantically faithful, and interpretable evaluations that remain robust under paraphrastic, semantic, and stylistic perturbations.
  arXiv  Detail & Related papers  (2026-01-23T11:59:13Z)
• Benchmarking Egocentric Clinical Intent Understanding Capability for Medical Multimodal Large Language Models [48.95516224614331]
  We introduce MedGaze-Bench, the first benchmark leveraging clinician gaze as a Cognitive Cursor to assess intent understanding across surgery, emergency simulation, and diagnostic interpretation.<n>Our benchmark addresses three fundamental challenges: visual homogeneity of anatomical structures, strict temporal-causal dependencies in clinical, and implicit adherence to safety protocols.
  arXiv  Detail & Related papers  (2026-01-11T02:20:40Z)
• ClinDEF: A Dynamic Evaluation Framework for Large Language Models in Clinical Reasoning [58.01333341218153]
  We propose ClinDEF, a dynamic framework for assessing clinical reasoning in LLMs through simulated diagnostic dialogues.<n>Our method generates patient cases and facilitates multi-turn interactions between an LLM-based doctor and an automated patient agent.<n>Experiments show that ClinDEF effectively exposes critical clinical reasoning gaps in state-of-the-art LLMs.
  arXiv  Detail & Related papers  (2025-12-29T12:58:58Z)
• Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models [51.91760712805404]
  We introduce VivaBench, a benchmark for evaluating sequential clinical reasoning in large language models (LLMs)<n>Our dataset consists of 1762 physician-curated clinical vignettes structured as interactive scenarios that simulate a (oral) examination in medical training.<n>Our analysis identified several failure modes that mirror common cognitive errors in clinical practice.
  arXiv  Detail & Related papers  (2025-10-11T16:24:35Z)
• ReEvalMed: Rethinking Medical Report Evaluation by Aligning Metrics with Real-World Clinical Judgment [10.958326795130112]
  We propose a clinically grounded Meta-Evaluation framework.<n>We define clinically grounded criteria spanning clinical alignment and key metric capabilities.<n>Our framework offers guidance for building more clinically reliable evaluation methods.
  arXiv  Detail & Related papers  (2025-09-30T21:00:47Z)
• Not What the Doctor Ordered: Surveying LLM-based De-identification and Quantifying Clinical Information Loss [1.514900191663287]
  De-identification in the healthcare setting is an application of NLP where automated algorithms are used to remove personally identifying information of patients (and, sometimes, providers)<n>With the recent rise of generative large language models (LLMs), there has been a corresponding rise in the number of papers that apply LLMs to de-identification.<n>This paper identifies three key limitations in the current literature: inconsistent reporting metrics direct comparisons, the inadequacy of traditional classification metrics in capturing errors, and lack of manual validation of automated metrics which aim to quantify these errors.
  arXiv  Detail & Related papers  (2025-09-17T22:37:15Z)
• MedScore: Generalizable Factuality Evaluation of Free-Form Medical Answers by Domain-adapted Claim Decomposition and Verification [51.82420076479152]
  We propose MedScore, a new pipeline to decompose medical answers into condition-aware valid facts and verify against in-domain corpora.<n>Our method extracts up to three times more valid facts than existing methods, reducing hallucination and vague references, and retaining condition-dependency in facts.
  arXiv  Detail & Related papers  (2025-05-24T01:23:09Z)
• GEMA-Score: Granular Explainable Multi-Agent Scoring Framework for Radiology Report Evaluation [7.838068874909676]
  Granular Explainable Multi-Agent Score (GEMA-Score) conducts both objective and subjective evaluation through a large language model-based multi-agent workflow.<n>GEMA-Score achieves the highest correlation with human expert evaluations on a public dataset.
  arXiv  Detail & Related papers  (2025-03-07T11:42:22Z)

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.