Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Non-equilibrium in the Cell

Non-equilibrium in the Cell

An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...

Introduction to Cognitive Psychology

Introduction to Cognitive Psychology

Cognitive psychology is the field of psychology dedicated to examining how people think. It attempts to explain how and why we think the way we do by studying the interactions among human thinking, emotion, creativity, language, and problem-solving, as well as other cognitive processes. Cognitive psychology studies how information is processed and manipulated in remembering, thinking, and knowing.
This field emerged in the mid-20th century, following a period dominated by behaviorism, which...

Natural and Artificial Concepts

Natural and Artificial Concepts

In psychology, concepts can be divided into two categories: natural and artificial. Natural concepts are formed through direct or indirect experiences. For example, consider the concept of snow. If you live in a place with regular snowfall, such as Essex Junction, Vermont, you know snow through direct experiences. You’ve seen it fall, touched it, shoveled it, and played in it. You recognize its texture, appearance, and even its smell. In contrast, if you live on an island like Saint...

You might also read

Related Articles

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

Sort by

Same author

Toward Evidence Synthesis of Adverse Events in Imbalanced Time-to-Event Data.

Journal of evidence-based medicine·2026

Same author

Likelihood ratios enhance clinical interpretation of metagenomic prediction of early-onset neonatal sepsis in preterm premature rupture of membranes (letter to the editor).

American journal of obstetrics and gynecology·2026

Same author

A novel model (SED-GNDE) integrating graph neural differential equations with selective electrodialysis process for nutrient prediction from synthetic wastewater.

Water research·2026

Same author

Trial design-aware funnel plot for publication bias assessment with noninferiority or equivalence objectives.

Journal of clinical epidemiology·2026

Same author

EFFECTIVENESS OF DISINFECTION METHODS FOR TOOTHBRUSHES: A SYSTEMATIC REVIEW AND META-ANALYSIS.

The journal of evidence-based dental practice·2026

Same author

Evaluating data extraction error by a large language model from randomised controlled trials: a large-scale empirical study.

BMJ evidence-based medicine·2026

Search research articles

Related Experiment Video

Updated: Jun 28, 2025

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

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

Published on: December 6, 2024

Exploring the Limits of Artificial Intelligence for Referencing Scientific Articles.

Emily M Graf¹, Jordan A McKinney¹, Alexander B Dye¹

¹Department of Obstetrics and Gynecology, University of Florida College of Medicine, Jacksonville, Florida.

American Journal of Perinatology

|April 23, 2024

Summary

Artificial intelligence (AI) chatbots like Google Bard, ChatGPT, and Chatsonic struggle with accurate obstetric literature referencing. Google Bard showed the highest accuracy, but all models frequently generated incorrect or non-existent citations.

More Related Videos

Author Spotlight: A Novel Setup to Conduct Naturalistic Laboratory Experiments with Real Human Actors in Scenarios

Author Spotlight: A Novel Setup to Conduct Naturalistic Laboratory Experiments with Real Human Actors in Scenarios

Published on: August 4, 2023

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

Related Experiment Videos

Last Updated: Jun 28, 2025

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

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

Published on: December 6, 2024

Author Spotlight: A Novel Setup to Conduct Naturalistic Laboratory Experiments with Real Human Actors in Scenarios

Author Spotlight: A Novel Setup to Conduct Naturalistic Laboratory Experiments with Real Human Actors in Scenarios

Published on: August 4, 2023

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

Area of Science:

Obstetrics and Gynecology
Artificial Intelligence in Medicine
Scientific Publishing

Background:

Artificial intelligence (AI) chatbots are increasingly used for information retrieval and scientific writing.
The reliability of AI-generated references in specialized medical fields like obstetrics is not well-established.
Accurate citation is crucial for scientific integrity and reproducibility.

Purpose of the Study:

To assess the accuracy of three popular AI chatbots (ChatGPT, Google Bard, Chatsonic) in generating references for obstetric randomized controlled trials (RCTs).
To compare the performance of these AI models in correctly citing key reference components (authors, title, journal, DOI).

Main Methods:

Three AI chatbots (ChatGPT, Google Bard, Chatsonic) were prompted to provide references for 44 obstetric RCTs published in 2020.
Reference accuracy was evaluated based on correct citation of authors, title, journal, and digital object identifier (DOI).
A permutation test was used for statistical comparison of AI model performance.

Main Results:

Google Bard achieved the highest accuracy, correctly citing 13.6% of references.
ChatGPT and Chatsonic showed significantly lower accuracy at 2.4% and 0%, respectively.
A majority of references generated by all AI models contained incorrect or non-existent digital object identifiers (DOIs).

Conclusions:

Authors must exercise caution when using AI chatbots for literature searches and scientific writing due to citation inaccuracies.
Despite current limitations, AI chatbots hold potential for synergistic collaboration with researchers to advance patient care.
Responsible AI implementation is vital to maintain the integrity of scientific information dissemination.