Multimodal LLMs are persistently miscalibrated, their calibration barely changes after fine-tuning or multimodal training, and they prefer giving answers to admitting ignorance, though prompting and temperature scaling can reduce overconfidence.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Unveiling Uncertainty: A Deep Dive into Calibration and Performance of Multimodal Large Language Models
Multimodal LLMs are persistently miscalibrated, their calibration barely changes after fine-tuning or multimodal training, and they prefer giving answers to admitting ignorance, though prompting and temperature scaling can reduce overconfidence.