> ## Documentation Index
> Fetch the complete documentation index at: https://docs.complior.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Bias Detection

> Screen LLM responses for bias across 15 EU Charter Art.21 protected characteristics with domain-aware scoring.

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

```typescript theme={null}
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

```typescript theme={null}
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:

```typescript theme={null}
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`.

<CardGroup cols={2}>
  <Card title="Error Handling" icon="triangle-exclamation" href="/sdk/errors">
    `BiasDetectedError` reference.
  </Card>

  <Card title="Safety Filter" icon="shield-halved" href="/sdk/safety">
    Content safety patterns and HITL gate.
  </Card>
</CardGroup>