The Mirage of LLM Guardrails: A Case Study in AI-Assisted Medical Note Manipulation

• URL: http://arxiv.org/abs/2607.24859v1
• Date: Sun, 26 Jul 2026 07:46:28 GMT
• Title: The Mirage of LLM Guardrails: A Case Study in AI-Assisted Medical Note Manipulation
• Abstract summary: We use AI-assisted medical note manipulation as a concrete case study.<n>First, we develop a reproducible manipulation pipeline that takes publicly available seed medical note templates.<n>Second, we conduct a systematic empirical evaluation of LLM guardrail robustness for medical note manipulation.<n>Third, we utilize a combination of automated metrics and human annotation-based metrics to assess the correctness of requested manipulations.
• Score: 7.091077137729042
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid deployment of large language models (LLMs) in healthcare settings makes the reliability of their built-in guardrails against malicious queries a question of urgent practical consequence. Yet the robustness of these mechanisms against deliberate misuse (in the healthcare context) remains poorly understood. In this paper, we investigate this question empirically, using AI-assisted medical note manipulation as a concrete case study. We make four novel contributions. First, we develop a reproducible manipulation pipeline that takes publicly available seed medical note templates and use commercial LLMs to produce customized manipulated notes by substituting patient names, provider identities, dates, and medical conditions across multiple model families, input formats, and prompt phrasings. Second, we conduct a systematic empirical evaluation of LLM guardrail robustness for medical note manipulation. Our experimental results reveal substantial weaknesses and inconsistencies in contemporary commercial LLM guardrails, including low refusal rates for several model families. Third, we utilize a combination of automated metrics and human annotation-based metrics to assess the correctness of requested manipulations. Fourth, we conduct a user-study to assess the believability of manipulated medical notes, finding that the best manipulations are visually indistinguishable from original documents to human raters. Finally, we discuss implications for responsible guardrail design in LLMs, AI safety policies, and the broader ethics of deploying LLMs in healthcare settings.

Related papers

• Assessing Automated Fact-Checking for Medical LLM Responses with Knowledge Graphs [12.287636586297756]
  The recent proliferation of large language models (LLMs) holds the potential to revolutionize healthcare.<n>This paper investigates the reliability and viability of using medical knowledge graphs (KGs) for the automated factuality evaluation of LLM-generated responses.<n>We introduce FAITH, a framework designed to probe the strengths and limitations of this KG-based approach.
  arXiv  Detail & Related papers  (2025-11-16T22:58:22Z)
• Structured Outputs Enable General-Purpose LLMs to be Medical Experts [50.02627258858336]
  Large language models (LLMs) often struggle with open-ended medical questions.<n>We propose a novel approach utilizing structured medical reasoning.<n>Our approach achieves the highest Factuality Score of 85.8, surpassing fine-tuned models.
  arXiv  Detail & Related papers  (2025-03-05T05:24:55Z)
• 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)
• Are We There Yet? Revealing the Risks of Utilizing Large Language Models in Scholarly Peer Review [66.73247554182376]
  Large language models (LLMs) have led to their integration into peer review.<n>The unchecked adoption of LLMs poses significant risks to the integrity of the peer review system.<n>We show that manipulating 5% of the reviews could potentially cause 12% of the papers to lose their position in the top 30% rankings.
  arXiv  Detail & Related papers  (2024-12-02T16:55:03Z)
• Advancing Healthcare Automation: Multi-Agent System for Medical Necessity Justification [0.0]
  This paper explores the application of Multi-Agent System (MAS) that utilize specialized LLM agents to automate Prior Authorization task. We demonstrate that GPT-4 checklist achieves an accuracy of 86.2% in predicting item-level judgments with evidence, and 95.6% in determining overall checklist judgment.
  arXiv  Detail & Related papers  (2024-04-27T18:40:05Z)
• Large Language Model Distilling Medication Recommendation Model [58.94186280631342]
  We harness the powerful semantic comprehension and input-agnostic characteristics of Large Language Models (LLMs)<n>Our research aims to transform existing medication recommendation methodologies using LLMs.<n>To mitigate this, we have developed a feature-level knowledge distillation technique, which transfers the LLM's proficiency to a more compact model.
  arXiv  Detail & Related papers  (2024-02-05T08:25:22Z)
• ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks [91.55895047448249]
  This paper presents ReEval, an LLM-based framework using prompt chaining to perturb the original evidence for generating new test cases. We implement ReEval using ChatGPT and evaluate the resulting variants of two popular open-domain QA datasets. Our generated data is human-readable and useful to trigger hallucination in large language models.
  arXiv  Detail & Related papers  (2023-10-19T06:37:32Z)
• Retrieving Evidence from EHRs with LLMs: Possibilities and Challenges [18.56314471146199]
  Large volume of notes often associated with patients together with time constraints renders manually identifying relevant evidence practically infeasible. We propose and evaluate a zero-shot strategy for using LLMs as a mechanism to efficiently retrieve and summarize unstructured evidence in patient EHR.
  arXiv  Detail & Related papers  (2023-09-08T18:44:47Z)
• Medical Misinformation in AI-Assisted Self-Diagnosis: Development of a Method (EvalPrompt) for Analyzing Large Language Models [4.8775268199830935]
  This study aims to assess the effectiveness of large language models (LLMs) as a self-diagnostic tool and their role in spreading healthcare misinformation.<n>We use open-ended questions to mimic real-world self-diagnosis use cases, and perform sentence dropout to mimic realistic self-diagnosis with missing information.<n>The results highlight the modest capabilities of LLMs, as their responses are often unclear and inaccurate.
  arXiv  Detail & Related papers  (2023-07-10T21:28:26Z)
• Self-Verification Improves Few-Shot Clinical Information Extraction [73.6905567014859]
  Large language models (LLMs) have shown the potential to accelerate clinical curation via few-shot in-context learning. They still struggle with issues regarding accuracy and interpretability, especially in mission-critical domains such as health. Here, we explore a general mitigation framework using self-verification, which leverages the LLM to provide provenance for its own extraction and check its own outputs.
  arXiv  Detail & Related papers  (2023-05-30T22:05:11Z)
• Appraising the Potential Uses and Harms of LLMs for Medical Systematic Reviews [21.546144601311187]
  Large language models (LLMs) offer potential to automatically generate literature reviews on demand. LLMs sometimes generate inaccurate (and potentially misleading) texts by hallucination or omission.
  arXiv  Detail & Related papers  (2023-05-19T17:09:19Z)
• Retrieval-Augmented and Knowledge-Grounded Language Models for Faithful Clinical Medicine [68.7814360102644]
  We propose the Re$3$Writer method with retrieval-augmented generation and knowledge-grounded reasoning. We demonstrate the effectiveness of our method in generating patient discharge instructions.
  arXiv  Detail & Related papers  (2022-10-23T16:34:39Z)

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.