A Holistic Approach to Undesired Content Detection in the Real World
Paper
• 2208.03274 • Published
Content moderation models and datasets - 2025
Models and datasets that support automatic content moderation
-
ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation
Paper • 2310.17389 • PublishedNote Papers ☝️
-
meta-llama/Llama-Guard-3-11B-Vision
Image-Text-to-Text • 11B • Updated • 1.39k • 67 -
meta-llama/Llama-Guard-3-8B
Text Generation • 8B • Updated • 136k • • 272 -
meta-llama/Prompt-Guard-86M
Text Classification • Updated • 26.7k • 311
zentropi-ai/cope-a-9b
Text Generation • Updated • 19Note Generative models☝️
-
unitary/unbiased-toxic-roberta
Text Classification • Updated • 49.8k • • 28 -
unitary/toxic-bert
Text Classification • 0.1B • Updated • 174k • • 213 -
KoalaAI/Text-Moderation
Text Classification • 0.1B • Updated • 28.3k • • 87 -
martin-ha/toxic-comment-model
Text Classification • Updated • 18.8k • • 67 -
NemoraAi/roberta-chat-moderation-X
Text Classification • 82.1M • Updated • 1 • 1 -
facebook/roberta-hate-speech-dynabench-r4-target
Text Classification • 0.1B • Updated • 996k • • 97
eliasalbouzidi/distilbert-nsfw-text-classifier
Text Classification • 67M • Updated • 6.18k • • 23Note Classification models ☝️
-
lmsys/toxic-chat
Viewer • Updated • 20.3k • 3.63k • 183
mmathys/openai-moderation-api-evaluation
Viewer • Updated • 1.68k • 249 • 35Note Datasets☝️
Task Exploration - Automatic Content Moderation
🤗2Note Other resources and collections☝️