Knowledge Tree
Relations (1)
related 12.00 — strongly supporting 12 facts
Large Language Models are the primary subject of medical hallucination research, as they are prone to generating misleading clinical information [1] and are the specific focus of detection benchmarks like MedHallu {fact:2, fact:7}. These hallucinations in Large Language Models pose significant risks to patient safety {fact:3, fact:11} and are studied through various frameworks and mitigation strategies {fact:1, fact:10, fact:12}.
Facts (12)
Sources
Medical Hallucination in Foundation Models and Their ... medrxiv.org 5 facts
claimMedical hallucinations in Large Language Models (LLMs) pose serious risks because incorrect dosages, drug interactions, or diagnostic criteria can lead to life-threatening outcomes.
claimMedical hallucinations in LLMs can manifest as incorrect diagnoses, the use of confusing or inappropriate medical terminology, or the presentation of contradictory findings within a patient’s case.
claimMedical hallucinations in LLMs manifest across various clinical tasks, including symptom diagnosis, patient management, and the interpretation of lab results and visual data.
claimLarge Language Models (LLMs) exhibit systematic errors known as medical hallucinations, where the models generate incorrect or misleading medical information that can adversely affect clinical decision-making and patient outcomes.
claimThe authors introduce a taxonomy for medical hallucination in Large Language Models to provide a structured framework for categorizing AI-generated medical misinformation.
Medical Hallucination in Foundation Models and Their Impact on ... medrxiv.org 5 facts
claimMedical hallucinations in large language models manifest across various clinical tasks, including symptom diagnosis, patient management, the interpretation of lab results, and the interpretation of visual data.
claimMedical hallucinations in LLMs pose serious risks because incorrect medical information, such as dosages, drug interactions, or diagnostic criteria, can lead to life-threatening outcomes.
claimThe authors explored structured prompting and reasoning scaffolds as mitigation strategies to assess their ability to reduce medical hallucination rates in LLMs.
claimThe authors propose a systematic framework for evaluating medical hallucinations in LLMs that aligns with the taxonomy presented in Table 2 of the paper.
claimMedical hallucinations in large language models are exacerbated by the complexity and specificity of medical knowledge, where subtle differences in terminology or reasoning can lead to significant misunderstandings.
A Comprehensive Benchmark for Detecting Medical Hallucinations ... researchgate.net 1 fact
claimMedHallu is the first benchmark specifically designed for medical hallucination detection in large language models.
A Comprehensive Benchmark for Detecting Medical Hallucinations ... aclanthology.org 1 fact
claimMedHallu is a benchmark designed for detecting medical hallucinations in large language models, consisting of 10,000 high-quality question-answer pairs derived from PubMedQA.