Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Anatomical Terminology01:20

Anatomical Terminology

Knowledge of anatomy is essential to understand human biology and medicine. Anatomists and health care professionals use standard terminology to describe the human body with more precision and no ambiguity. Anatomical terms have mostly Greek and Latin-derived roots. Because these languages are rarely used in conversation, the meaning of words remains the same. Each term is made up of a root in between the prefixes and suffixes. The root of a term often refers to an organ, tissue, or condition,...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

The middle hepatic artery: prevalence and origin patterns of a distinct segment 4 artery.

Surgical and radiologic anatomy : SRA·2026
Same author

Anatomical Variability of the Proximal Femur: A Morphometric Study Relevant to Orthopedic Implant Design.

Medeniyet medical journal·2026
Same author

Thin cortical translucent area of the iliac wing: morphometric analysis and implications for surgical safety.

Journal of orthopaedics and traumatology : official journal of the Italian Society of Orthopaedics and Traumatology·2026
Same author

Is artificial intelligence getting better at anatomy? A two-year review of ChatGPT's free public versions.

Anatomical sciences education·2026
Same author

Hepatic arterial variants on CT angiography: applicability and coverage of the CRL classification system.

Surgical and radiologic anatomy : SRA·2026
Same author

Comment on ''The zygomatico-orbital artery: anatomical study of zygomatico-orbital artery: implication for eyelid reconstruction and improving the safety of temporal augmentation''.

Surgical and radiologic anatomy : SRA·2026

Related Experiment Video

Updated: Jul 16, 2026

Fine-Tuning Large Language Models Using Entity Hallucination Index for Text Summarization
04:16

Fine-Tuning Large Language Models Using Entity Hallucination Index for Text Summarization

Published on: January 9, 2026

Reference Hallucination, Citation Reliability, and Readability of Large Language Models in Anatomy-Related Question

Mehmet Ülkir1, Bahattin Paslı1

  • 1Department of Anatomy, Faculty of Medicine, Hacettepe University, Ankara, Türkiye.

Clinical Anatomy (New York, N.Y.)
|July 15, 2026
PubMed
Summary

Large language models (LLMs) show promise in anatomy education but struggle with accurate citations. ChatGPT 5.2 had fewer reference hallucinations than Gemini 3 Pro and DeepSeek V3.2, though human verification is still crucial.

Keywords:
anatomy educationcitation accuracylarge language modelsreadabilityreference hallucination

More Related Videos

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Related Experiment Videos

Last Updated: Jul 16, 2026

Fine-Tuning Large Language Models Using Entity Hallucination Index for Text Summarization
04:16

Fine-Tuning Large Language Models Using Entity Hallucination Index for Text Summarization

Published on: January 9, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Area of Science:

  • Medical Education Technology
  • Artificial Intelligence in Healthcare
  • Anatomy Education

Background:

  • Large language models (LLMs) are increasingly adopted in medical education and academic writing.
  • Significant concerns exist regarding reference hallucination, citation accuracy, and the overall reliability of LLM-generated content in scientific contexts.

Purpose of the Study:

  • To evaluate the performance of ChatGPT 5.2, Gemini 3 Pro, and DeepSeek V3.2 in generating anatomy-related responses.
  • To assess bibliographic reference accuracy, citation content consistency, and readability of LLM-generated content across six anatomical categories.

Main Methods:

  • 120 open-ended anatomy questions were posed to ChatGPT 5.2, Gemini 3 Pro, and DeepSeek V3.2.
  • Bibliographic components (author, title, journal, publication details, PMID) of 1800 references were verified against indexed sources.
  • Citation content consistency was rated on a Likert scale, and readability was assessed using standard indices (Flesch, Coleman-Liau, SMOG).

Main Results:

  • ChatGPT 5.2 exhibited the lowest hallucination rate (23.2%), compared to Gemini 3 Pro (45.8%) and DeepSeek V3.2 (47.5%).
  • DeepSeek V3.2 showed higher accuracy in individual bibliographic components, but PMID accuracy was low across all models (25.1%-57.6%).
  • ChatGPT 5.2 had the highest citation content consistency (67.2%), significantly outperforming Gemini 3 Pro (42.5%) and DeepSeek V3.2 (41.0%).

Conclusions:

  • While LLMs can produce plausible anatomy content, significant limitations in reference accuracy and citation reliability persist.
  • ChatGPT 5.2 demonstrated superior performance in minimizing reference hallucinations and ensuring citation consistency among the evaluated models.
  • Human oversight and verification are essential before integrating LLM-generated references into academic and educational materials.