Hallucination Rates and Reference Accuracy of ChatGPT and Bard for Systematic Reviews: Comparative Analysis

Mikaël Chelli   ¹ , MSc, MD ;   Jules Descamps   ² , MSc, MD ;   Vincent Lavoué   ¹ , MD ;   Christophe Trojani   ¹ , MD, PhD ;   Michel Azar   ¹ , MD ;   Marcel Deckert   ³ , PhD ;   Jean-Luc Raynier   ¹ , MSc, MD ;   Gilles Clowez   ¹ , MD ;   Pascal Boileau   ¹ , MD, PhD ;   Caroline Ruetsch-Chelli   ³ , MSc, MD

¹ Institute for Sports and Reconstructive Bone and Joint Surgery, Groupe Kantys, Nice, France

² Orthopedic and Traumatology Unit, Hospital Lariboisière, Assistance Publique-Hôpitaux de Paris, Paris, France

³ Université Côte d’Azur, INSERM, C3M, Team Microenvironment, Signalling and Cancer, Nice, France