Marking the Wrong Symptoms: Evaluating LLM Watermarks in Medical Texts

• URL: http://arxiv.org/abs/2607.20462v1
• Date: Sat, 16 May 2026 08:16:08 GMT
• Title: Marking the Wrong Symptoms: Evaluating LLM Watermarks in Medical Texts
• Abstract summary: We present the first rigorous study of how watermarks affect medical performance, benchmarking 5 watermarking schemes across 11 LLMs and 7 VLMs.<n>Our results reveal that watermarking can induce substantial degradation across multiple failure modes, including lexical corruption, hallucinated terminology, and amplified misattribution or omission of image findings.<n>Our findings establish domain-specific evaluation as a prerequisite for the safe deployment of watermarked models in medicine.
• Score: 9.564559994172438
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are increasingly integrated into clinical workflows, stressing the need for reliable traceability of model-generated output with watermarking. Yet, most watermarks are evaluated on general-purpose benchmarks, leaving domains like medicine, where small token-level perturbations can result in significant semantic changes, underexplored. In this work, we present the first rigorous study of how LLM watermarks affect medical performance, benchmarking 5 watermarking schemes across 11 LLMs and 7 VLMs on various tasks spanning unimodal and multimodal clinical reasoning. Importantly, we complement existing evaluations by introducing a human-expert-validated pipeline for systematically auditing medical reasoning quality, terminological precision, and induced hallucinations. Our results reveal that watermarking can induce substantial degradation across multiple failure modes, including lexical corruption, hallucinated terminology, and amplified misattribution or omission of image findings. Notably, we find that the absence of domain-specific analyses, combined with aggregate metrics that miss failures inherent to clinical text, can systematically obscure practical watermark-induced degradations. Our findings establish domain-specific evaluation as a prerequisite for the safe deployment of watermarked models in medicine, where current benchmarks can otherwise mask clinically consequential failures.

Related papers

• 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)
• Lost in the Hype: Revealing and Dissecting the Performance Degradation of Medical Multimodal Large Language Models in Image Classification [14.247959730104085]
  multimodal large language models (MLLMs) have sparked an unprecedented wave of applications in the field of medical imaging analysis.<n>However, medical image classification reveals a sobering reality: state-of-the-art medical MLLMs consistently underperform compared to traditional deep learning models.<n>In this paper, we conduct extensive experiments on 14 open-source medical MLLMs across three representative image classification datasets.
  arXiv  Detail & Related papers  (2026-04-09T15:07:26Z)
• Clinical Cognition Alignment for Gastrointestinal Diagnosis with Multimodal LLMs [63.535652574541764]
  Multimodal Large Language Models (MLLMs) have demonstrated remarkable potential in medical image analysis.<n>Their application in gastrointestinal endoscopy is currently hindered by two critical limitations.<n>We propose a novel Clinical-Cognitive-Aligned (CogAlign) framework to address these challenges.
  arXiv  Detail & Related papers  (2026-03-21T07:47:37Z)
• X-Mark: Saliency-Guided Robust Dataset Ownership Verification for Medical Imaging [67.85884025186755]
  High-quality medical imaging datasets are essential for training deep learning models, but their unauthorized use raises serious copyright and ethical concerns.<n>Medical imaging presents a unique challenge for existing dataset ownership verification methods designed for natural images.<n>We propose X-Mark, a sample-specific clean-label watermarking method for chest x-ray copyright protection.
  arXiv  Detail & Related papers  (2026-02-10T00:03:43Z)
• Rethinking Toxicity Evaluation in Large Language Models: A Multi-Label Perspective [104.09817371557476]
  Large language models (LLMs) have achieved impressive results across a range of natural language processing tasks.<n>Their potential to generate harmful content has raised serious safety concerns.<n>We introduce three novel multi-label benchmarks for toxicity detection.
  arXiv  Detail & Related papers  (2025-10-16T06:50:33Z)
• Toward Reliable Clinical Coding with Language Models: Verification and Lightweight Adaptation [3.952186976672079]
  We show that lightweight interventions, including prompt engineering and small-scale fine-tuning, can improve accuracy without the computational overhead of search-based methods.<n>To address hierarchically near-miss errors, we introduce clinical code verification as both a standalone task and a pipeline component.
  arXiv  Detail & Related papers  (2025-10-08T23:50:58Z)
• Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Texts [14.42794744856763]
  We introduce the Factuality-Weighted Score (FWS), a metric prioritizing factual accuracy beyond coherence to guide watermarking deployment in medical domains.<n>Our evaluation shows current watermarking methods substantially compromise medical factuality, with entropy shifts degrading medical entity representation.<n>These findings underscore the need for domain-aware watermarking approaches to preserve the integrity of medical content.
  arXiv  Detail & Related papers  (2025-09-09T13:54:34Z)
• 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)
• Metrics that matter: Evaluating image quality metrics for medical image generation [48.85783422900129]
  This study comprehensively assesses commonly used no-reference image quality metrics using brain MRI data.<n>We evaluate metric sensitivity to a range of challenges, including noise, distribution shifts, and, critically, morphological alterations designed to mimic clinically relevant inaccuracies.
  arXiv  Detail & Related papers  (2025-05-12T01:57:25Z)
• Pathology-Aware Adaptive Watermarking for Text-Driven Medical Image Synthesis [14.661742509140995]
  MedSign is a deep learning-based watermarking framework specifically designed for text-to-medical image synthesis.<n>We generate a pathology localization map using cross-attention between medical text tokens and the diffusion denoising network.<n>We optimize the LDM decoder to incorporate watermarking during image synthesis.
  arXiv  Detail & Related papers  (2025-03-11T11:55:14Z)
• 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)
• WatME: Towards Lossless Watermarking Through Lexical Redundancy [58.61972059246715]
  This study assesses the impact of watermarking on different capabilities of large language models (LLMs) from a cognitive science lens. We introduce Watermarking with Mutual Exclusion (WatME) to seamlessly integrate watermarks.
  arXiv  Detail & Related papers  (2023-11-16T11:58:31Z)

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.