Content moderation unsafe tagging
Multi-label classification of user content for moderation (hate speech, spam, graphic violence, sexual content).
STop tier. Meets A, and the payoff is major with high confidence.5.90
Key facts
- Vertical
- Software & tech
- Function
- Social & creator
- Status
- Seen in the wild
- Volume
- high
- Value
- major
- Risk
- high
- Evidence
- described plan
- Flags
- human-review
Source: https://arxiv.org/pdf/2407.10995
Build this with a classifier
Define a typed decision with a bounded answer, then evaluate it on examples.
{
"decision_type": "yes_no",
"question": "Does this input match the decision in “Content moderation unsafe tagging”?",
"input": "<input to classify>",
"output": "yes | no"
}Related use cases
Cite this
Copy a link in your preferred format.