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

Bias

Schema-driven detector documentation.

BIASactiveP25 params2 examples
Detector Metadata
Capability catalog entry from all_detectors.json.

Categories

FAIRNESSCONTENT

Supported Asset Types

TXTTABLEURL

Recommended Model

valurank/distilroberta-bias

Notes

Detects biased language patterns for fairness governance and moderation workflows.

Parameters
Configuration parameters for the Bias detector. Shared from `BiasDetectorConfig`.
ParameterTypeRequiredDescriptionDefaultConstraints
enabled_patternsarrayNoSpecific bias signals to detect
enabled_patterns[]enumNoBias detector pattern types Allowed values: gender_bias, racial_bias, age_bias, religious_bias, political_bias
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