Skip to Content
Unified docs shell with shared Classifyre tokens and acid-green highlight accents.
DetectorsHate Speech

Hate Speech

Schema-driven detector documentation.

HATE_SPEECHplannedP24 params2 examples
Detector Metadata
Capability catalog entry from all_detectors.json.

Categories

CONTENTCOMPLIANCE

Supported Asset Types

TXTTABLEURL

Recommended Model

facebook/roberta-hate-speech-dynabench-r4-target

Notes

Flags targeted hateful language for moderation and policy reporting, including German-language coverage.

Parameters
Configuration parameters for the Hate Speech detector. Shared from `GenericDetectorConfig`.
ParameterTypeRequiredDescriptionDefaultConstraints
enabled_patternsarray | nullNoList of enabled pattern namesnull
severity_thresholdenum | nullNoMinimum severity to reportnull
confidence_thresholdnumberNoMinimum confidence to report (0-1)0.7min 0, max 1
max_findingsinteger | nullNoMaximum number of findings to returnnull