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

• Main Authors: Mikaël Chelli (Author), Jules Descamps (Author), Vincent Lavoué (Author), Christophe Trojani (Author), Michel Azar (Author), Marcel Deckert (Author), Jean-Luc Raynier (Author), Gilles Clowez (Author), Pascal Boileau (Author), Caroline Ruetsch-Chelli (Author)
• Format: Book
• Published: JMIR Publications, 2024-05-01T00:00:00Z.
• Subjects: article
• Online Access: Connect to this object online.

BackgroundLarge language models (LLMs) have raised both interest and concern in the academic community. They offer the potential for automating literature search and synthesis for systematic reviews but raise concerns regarding their reliability, as the tendency to generate unsupported (hallucinated...