Article

Large Language Models Are Highly Vulnerable to Adversarial Hallucination Attacks in Clinical Decision Support: A Multi-Model Assurance Analysis

2025-03-19

Abstract excerpt

<h4>Background</h4> Large language models (LLMs) show promise in clinical contexts but can generate false facts (often referred to as “hallucinations”). One subset of these errors arises from adversarial attacks, in which fabricated details embedded in prompts lead the model to produce or elaborate on the false information. We embedded fabricated content in clinical prompts to elicit adversarial hallucination att...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 218fb00a-8408-5c0d-92ff-8b517d8abf2f
DOI: 10.1101/2025.03.18.25324184

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Large Language Models Are Highly Vulnerable to Adversarial Hallucination Attacks in Clinical Decision Support: A Multi-Model Assurance AnalysisDOI 10.1101/2025.03.18.25324184Read

Rethinking Medical LLM Hallucinations: A System-Level SurveySemantic proximity Read

An interdisciplinary, randomized, single-blind evaluation of state-of-the-art large language models for their implications and risks in medical diagnosis and managementSemantic proximity Read

Understanding the Inner Workings of Large Language Models in MedicineSemantic proximity Read

Beyond Benchmarks: Dynamic, Automatic And Systematic Red-Teaming Agents For Trustworthy Medical Language ModelsSemantic proximity Read

Learning the Phenotype of Medical HallucinationsSemantic proximity Read

Red-Teaming Medical AI: Systematic Adversarial Evaluation of LLM Safety Guardrails in Clinical ContextsSemantic proximity Read

Medical Hallucination in Foundation Models and Their Impact on HealthcareSemantic proximity Read

Evaluating anti-LGBTQIA+ medical bias in large language modelsSemantic proximity Read

Evaluating Large Language Models for Drafting Emergency Department Discharge SummariesSemantic proximity Read

Emergent Misinformation Genesis in Multi-Agent LLM Clinical PipelinesSemantic proximity Read