Medical Large Language Models (LLMs) exhibit overconfidence, which is linked to poor calibration and results in outputs presenting an unwarranted level of certainty, as noted by Cao et al. (2021) and Hagendorff et al. (2023).

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 (1)

• overconfidence bias concept