This is the official repository for the toolbox developed for the study -- "Benchmarking Trustworthiness of Multimodal Large Language Models: A Comprehensive Study" (MultiTrust).
The code and datasets will be released soon.
Barath19/MMTrustEval
A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust)
PythonCC-BY-SA-4.0