Abstention thresholding allows AI models to refrain from providing conclusive guidance when they generate multiple hypotheses without a single decisive answer, as discussed by Geng et al. (2024) and Steyvers et al. (2024).

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)

• AI models concept