Home›Biases›IBI-00126
IBI-001265 - Criticalpublie

LLM Bias

Biais dans les LLMs

IBI Score
9.2
out of 10
Severity5_critique
Frequencysystematique
Scope groups5
Detection difficulty4
🇫🇷 Définition (FR)

Reproduction de stéréotypes et discriminations dans les grands modèles de langage.

🇬🇧 Definition (EN)

Reproduction of stereotypes and discriminations in large language models.

TriAxis Taxonomy

Structural Classification

O
Origin
O2
Computational & Statistical
L
Lifecycle
L2
Representation
S
Specific
S22
Linguistic bias
💡
Concrete Example

Les LLMs associent les personnes musulmanes à la violence plus souvent que les autres groupes.

📊 Detection Metrics

Demographic Parity DifferenceDisparate Impact RatioEqualized Odds Difference

⚙ Alert Thresholds

Disparate Impact Ratio0.8
Equalized Odds Difference0.1
Demographic Parity Difference0.1

📚 Sources & Scientific References

🛡 Impact & Mitigation

🎯 Vulnerable groups impacted

Arab / MENA personsWomen

🛠 Mitigation methodologies

  • SHAP_GROUP : SHAP Group Analysis
  • AUDIT_TIERS : Third-party Audit

🏢 Sectors concerned

Media & Social Platforms (Risk: /5)HR & Recruitment (Risk: /5)Justice & Security (Risk: /5)

⚖ Applicable regulations

🇪🇺 Europe
  • •
    AI_ACT_10 : AI Act (UE) 2024/1689
  • •
    AI_ACT_13 : AI Act (UE) 2024/1689
🌍 International
  • •
    ISO_42001 : ISO/IEC 42001:2023
  • •
    UNESCO_2021 : UNESCO - Recommandation sur l'éthique de l'IA
  • •
    OECD_AI_PRINCIPLES : OCDE - Principes IA
  • •
    COE_AI_CONVENTION_INT : Conseil de l'Europe - Convention IA

📋 Metadata

Contributor
Mohamadou SIDIBE
Institution
AI BIAIS INITIATIVE
Version
1
Created on
October 14, 2026
Updated on
November 4, 2026
UUID
1204572b-133f-4424-980d-cb63f6428958

Explore other biases

250 documented biases, classified by the TriAxis taxonomy.