Home›Biases›IBI-00143
IBI-001434 - Severepublie

Word Embedding Bias

Biais dans les embeddings de mots

IBI Score
8.0
out of 10
Severity4_grave
Frequencysystematique
Scope groups4
Detection difficulty4
🇫🇷 Définition (FR)

Associations stéréotypées dans les représentations vectorielles des mots.

🇬🇧 Definition (EN)

Stereotyped associations in word vector representations.

TriAxis Taxonomy

Structural Classification

O
Origin
O2
Computational & Statistical
L
Lifecycle
L5
Learning
S
Specific
S22
Linguistic bias
💡
Concrete Example

« Homme » est associé à « programmeur » et « femme » à « infirmière » dans Word2Vec.

📊 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

Women

🛠 Mitigation methodologies

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

🏢 Sectors concerned

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

⚖ Applicable regulations

🇪🇺 Europe
  • •
    AI_ACT_10 : AI Act (UE) 2024/1689
  • •
    AI_ACT_15 : AI Act (UE) 2024/1689
  • •
    AI_ACT_9 : AI Act (UE) 2024/1689
🇺🇸 United States
  • •
    US_CO_SB24_205 : Colorado AI Act (SB 24-205)
  • •
    US_NIST_AI_RMF : NIST AI Risk Management Framework 1.0
🌍 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
🌐 autre
  • •
    SG_AI_GOVERNANCE : Singapour - AI Governance Framework

📋 Metadata

Contributor
Mohamadou SIDIBE
Institution
AI BIAIS INITIATIVE
Version
1
Created on
October 14, 2026
Updated on
November 4, 2026
UUID
43a8d2d3-1b1f-482e-b499-5eef7548ca5c

Explore other biases

250 documented biases, classified by the TriAxis taxonomy.