<ul data-eligibleForWebStory="false"><li>Phi-3-Vision's integration aligns with Microsoft’s Responsible AI principles, incorporating safety post-training in different stages to enhance performance.</li><li>Safety training datasets include both text-only RAI datasets and in-house Multi-Modal RAI datasets covering various harm categories from public and internal benchmarks.</li><li>Phi-3-Vision's RAI performance was evaluated across internal and public benchmarks, showcasing notable improvements in safety and overall performance.</li><li>Results demonstrate that safety post-training can aid Phi-3-Vision in enhancing RAI performance across various categories.</li></ul>

Benchmarking Multimodal Safety: Phi-3-Vision's Robust RAI Performance

Discover more