ReDiT: re-evaluating large visual question answering model confidence by defining input scenario difficulty and applying temperature mapping
Crossref DOI link: https://doi.org/10.1007/s00530-024-01629-w
Published Online: 2025-01-06
Published Print: 2025-02
Update policy: https://doi.org/10.1007/springer_crossmark_policy
Al-Shouha, Modafar
Szűcs, Gábor
Text and Data Mining valid from 2025-01-06
Version of Record valid from 2025-01-06
Article History
Received: 14 February 2024
Accepted: 15 December 2024
First Online: 6 January 2025
Declarations
:
: The authors declare no competing interests.