ShieldstralMistral AI
|
||||||
Related Products
|
||||||
About
Shieldstral is a 3B open-weights, policy-adaptive multimodal safety classifier designed to evaluate text, images, and text-plus-image content using policies defined at inference time. Instead of relying on a fixed taxonomy of harm categories, it frames moderation as a binary question-answering task: users provide an instruction describing the evaluation context and strictness, a yes-or-no safety question, and the content to judge. The model reads the “yes” and “no” logits and converts them into a continuous, calibrated safety score, allowing applications to threshold or rank results by confidence rather than depend on a single discrete label. This formulation unifies prompt classification, response moderation, refusal detection, toxicity detection, and multimodal safety in one interface, while letting teams adapt policies without retraining the model. Shieldstral can evaluate prompts, responses, prompt-response pairs, images, and images with accompanying text.
|
About
Custom neural network trained to triage reported content. For years, social networks have relied on users to report abuse, hate speech, and other types of online harms. Reports are sent to moderation teams who review each abuse report individually. Many platforms receive thousands of reports daily, most of which can be closed without taking action. Meanwhile, reports containing time-sensitive content — suicide threats, violence, terrorism, and child abuse — risk going unseen or not being reviewed until it’s too late. There are legal implications as well. The German law known as NetzDG says that platforms must remove reported hate speech and illegal content within 24 hours — or face fines of up to 50 million euros. Similar laws concerning reported content are being introduced in France, Australia, the UK, and across the globe. With Two Hat’s reported content product Predictive Moderation, platforms can train a custom AI model on their moderation team’s consistent decisions.
|
|||||
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
|||||
Audience
AI platform teams that need customizable, multimodal content moderation without retraining a separate safety model for every policy
|
Audience
Platform owners that need a predictive moderation solution to use trained custom AI models for their moderation teams
|
|||||
Support
Phone Support
24/7 Live Support
Online
|
Support
Phone Support
24/7 Live Support
Online
|
|||||
API
Offers API
|
API
Offers API
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
No information available.
Free Version
Free Trial
|
Pricing
No information available.
Free Version
Free Trial
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Webinars
Live Online
In Person
|
Training
Documentation
Webinars
Live Online
In Person
|
|||||
Company InformationMistral AI
Founded: 2023
France
mistral.ai/news/shieldstral/
|
Company InformationTwo Hat
Founded: 2012
Canada
www.twohat.com/predictive-moderation-template/
|
|||||
Alternatives |
Alternatives |
|||||
|
|
|
|||||
|
|
|
|||||
|
|
||||||
Categories |
Categories |
|||||
Integrations
Mistral AI
|
||||||
|
|
|