IBI-002404 - Severepublie
Demographic Composition Bias
Biais de composition démographique
IBI Score
7.4
out of 10
Severity4_grave
Frequencysystematique
Scope groups4
Detection difficulty2
🇫🇷 Définition (FR)
LLMs générant des histoires ou exemples avec des distributions démographiques non représentatives.
🇬🇧 Definition (EN)
LLMs generating stories or examples with non-representative demographic distributions.
TriAxis Taxonomy
Structural Classification
O
Origin
O2
Computational & Statistical
L
Lifecycle
L2
Representation
S
Specific
S16
Exclusion bias
💡
Concrete Example
Demandez à un LLM de générer 10 portraits de CEO : 9 seront blancs, tous seront des hommes.
📊 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
- •Evaluating the Social Impact of Generative AI Systems in Systems and SocietyIrene Solaiman, Zeerak Talat, William Agnew, Lama Ahmad, Su Lin Blodgett, Dylan Baker, Hal Daumé III, Sasha Luccioni, Margaret Mitchell, et al. (2023)
- •Missing the Margins: A Systematic Literature Review on the Demographic Representativeness of LLMsIndira Sen, Marlene Lutz, Elisa Rogers, David Garcia, Markus Strohmaier (2025)
- •Large language models that replace human participants can harmfully misportray and flatten identity groupsAngelina Wang, Jamie Morgenstern, John P. Dickerson (2025)
🛡 Impact & Mitigation
🎯 Vulnerable groups impacted
WomenBlack / Afro-descendant
🛠 Mitigation methodologies
- DEMO_PARITY : Demographic Parity
- 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
🌍 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
84e7ef90-c374-4e83-84e5-af3a52bbff33
Explore other biases
250 documented biases, classified by the TriAxis taxonomy.