Tag
Mistral AI releases Shieldstral, a 3B open-weights multimodal safety classifier that treats content moderation as a policy-adaptive question-answering task, outperforming models up to 7x its size without retraining.
Shieldstral is a 3B parameter multimodal safety classifier that achieves state-of-the-art performance on safety benchmarks by formulating content moderation as a binary question-answering task, matching or outperforming models nearly 7 times its size.
Mistral AI releases Shieldstral-1.0-3B, a compact multimodal safety classifier that adapts to natural-language safety policies at inference time, supporting text, image, and text+image moderation.
SingGuard is a policy-adaptive multimodal LLM guardrail model for text, image, and multilingual safety moderation, featuring dynamic reasoning and a new benchmark SingGuard-Bench. It achieves state-of-the-art results across multiple datasets.