IBI Score
9.2
out of 10
Severity5_critique
Frequencysystematique
Scope groups5
Detection difficulty4
🇫🇷 Définition (FR)
Tendance à favoriser les membres de son propre groupe au détriment des autres.
🇬🇧 Definition (EN)
Tendency to favor members of one's own group at the expense of others.
TriAxis Taxonomy
Structural Classification
O
Origin
O3
Human-Cognitive
L
Lifecycle
L6
Evaluation
S
Specific
S18
Group attribution bias
💡
Concrete Example
Un LLM favorise les cultures occidentales dans ses recommandations.
📊 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
- •Experiments in Intergroup DiscriminationTajfel, H. (1970)
- •Generative language models exhibit social identity biasesYara Kyrychenko, Steve Rathje, Tiancheng Hu, Nigel Collier, Sander van der Linden, Jon Roozenbeek (2024)
🛡 Impact & Mitigation
🎯 Vulnerable groups impacted
Black / Afro-descendantArab / MENA personsMinority language speakersRural areasNon-binary personsYouth (18-25)Seniors (60+)Motor disabilityAsian personsWorking classWomenLGBTQ+ persons
🛠 Mitigation methodologies
- DEMO_PARITY : Demographic Parity
- SHAP_GROUP : SHAP Group Analysis
- 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
🇺🇸 United States
- •US_TX_TRAIGA : Texas Responsible AI Governance Act (HB 149)
🌍 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
🇫🇷 France
- •FR_CNIL_AI : CNIL - Recommandations IA
🌐 Canada
- •CA_AIDA : Canada - Loi sur l'IA et les données (AIDA)
📋 Metadata
Contributor
Mohamadou SIDIBE
Institution
AI BIAIS INITIATIVE
Version
1
Created on
October 14, 2026
Updated on
November 4, 2026
UUID
e04485f4-2777-4b02-ae48-7dad838a6479
Explore other biases
250 documented biases, classified by the TriAxis taxonomy.