Respondents identified insufficient training data (31 mentions) and biased training data (31 mentions) as the most frequently cited causes of AI hallucinations, followed by limitations in model architecture (30), lack of real-world context (26), overconfidence in AI-generated responses (24), and inadequate transparency of AI decision-making (14).

Authors

• Person: Not available Organization: medRxiv
  Medical Hallucination in Foundation Models and Their ...

Sources

• Medical Hallucination in Foundation Models and Their ... www.medrxiv.org medRxiv via serper

Referenced by nodes (2)

• training data concept
• AI hallucinations concept