Bias Detection

The bias check post-hook screens LLM responses for discriminatory language across all 15 protected characteristics defined in the EU Charter of Fundamental Rights, Article 21.

15 Protected Characteristics

Characteristic	Example Patterns	Severity Range
`sex`	Gender stereotypes, role enforcement, selection bias	MEDIUM–HIGH
`race`	Racial generalizations, supremacy language	MEDIUM–CRITICAL
`colour`	Skin colour capability bias	HIGH
`ethnic_origin`	Ethnic generalizations, xenophobic directives	MEDIUM–HIGH
`social_origin`	Class-based bias, preferential treatment	MEDIUM
`genetic_features`	Genetic determinism, genetic screening for access	HIGH–CRITICAL
`language`	Language-based competence bias	LOW–MEDIUM
`religion`	Religious stereotypes, discrimination directives	MEDIUM–HIGH
`political_opinion`	Political stereotyping, discrimination	MEDIUM–HIGH
`national_minority`	Minority exclusion, group slurs	HIGH–CRITICAL
`property`	Wealth-based discrimination, access denial	MEDIUM–HIGH
`birth`	Birth-based discrimination, origin prejudice	MEDIUM
`disability`	Capability stereotypes, exclusion, slurs	HIGH–CRITICAL
`age`	Age-based capability bias (both older and younger)	MEDIUM–HIGH
`sexual_orientation`	Pathologization, discrimination	HIGH–CRITICAL
`nationality`	Nationality stereotypes, discrimination	HIGH

Severity Weights

Each pattern has a severity level that determines its contribution to the aggregate score:

Severity	Weight	Description
`LOW`	0.1	Stereotyping, mild generalizations
`MEDIUM`	0.3	Differential treatment language
`HIGH`	0.6	Discriminatory outcome language
`CRITICAL`	1.0	Explicit slurs, hate speech, supremacy

Scoring Formula

pattern weight × domain multiplier → per-finding score
sum(per-finding scores) → aggregate score
aggregate score > threshold → action (warn or block)

Domain Profiles

Each domain profile sets a default threshold and weight multipliers for characteristics that are especially sensitive in that context.

General (default)

Threshold: 0.3
Multipliers: None (all at 1.0×)

HR / Recruitment

The strictest profile — HR is classified as high-risk under EU AI Act Art.6(2).

Threshold: 0.15
2.0× multipliers: sex, race, age, disability, ethnic_origin
1.5× multipliers: religion, sexual_orientation, nationality, political_opinion

import { complior } from '@complior/sdk';
import OpenAI from 'openai';

const client = complior(new OpenAI(), {
  domain: 'hr',
  biasAction: 'block',
  // Threshold auto-set to 0.15, multipliers applied
});

Finance

Strict on property and social origin for credit/loan decisions.

Threshold: 0.2
2.0× multipliers: property, social_origin
1.5× multipliers: race, nationality, birth

Healthcare

Strict on disability and genetic features for medical decisions.

Threshold: 0.2
2.0× multipliers: disability, genetic_features
1.5× multipliers: age, race, sex

Education

Strict on age, disability, and social origin for admissions/grading.

Threshold: 0.2
2.0× multipliers: age, disability, social_origin
1.5× multipliers: language, ethnic_origin, birth

Configuration

import { complior } from '@complior/sdk';
import OpenAI from 'openai';

const client = complior(new OpenAI(), {
  domain: 'finance',       // Activates finance profile
  biasThreshold: 0.15,     // Override profile default (0.2)
  biasAction: 'block',     // Throw BiasDetectedError
});

Field	Type	Default	Description
`domain`	`Domain`	`undefined`	Activates domain profile (sets threshold + multipliers)
`biasThreshold`	`number`	Profile default	Override threshold (0–1, lower = stricter)
`biasAction`	`'warn' \| 'block'`	`'warn'`	Action on threshold exceeded

BiasEvidence

When a finding is detected, it produces a BiasEvidence object:

interface BiasEvidence {
  readonly characteristic: string; // e.g., 'sex', 'race'
  readonly severity: string;       // 'LOW' | 'MEDIUM' | 'HIGH' | 'CRITICAL'
  readonly evidence: string;       // Matched text
  readonly score: number;          // weight × domain multiplier
}

In warn mode, findings are available in response metadata. In block mode, they are on the BiasDetectedError.

Error Handling

BiasDetectedError reference.

Safety Filter

Content safety patterns and HITL gate.

Get Started

Scan (Static Analysis)

Eval (Dynamic Testing)

Fix (Auto-Remediation)

Agent Passport

Compliance Documents

SDK (Runtime)

MCP Server

Standards

Guides

15 Protected Characteristics

Severity Weights

Scoring Formula

Domain Profiles

General (default)

HR / Recruitment

Finance

Healthcare

Education

Configuration

BiasEvidence

Error Handling

Safety Filter

​15 Protected Characteristics

​Severity Weights

​Scoring Formula

​Domain Profiles

​General (default)

​HR / Recruitment

​Finance

​Healthcare

​Education

​Configuration

​BiasEvidence

Error Handling

Safety Filter

15 Protected Characteristics

Severity Weights

Scoring Formula

Domain Profiles

General (default)

HR / Recruitment

Finance

Healthcare

Education

Configuration

BiasEvidence