IBI Score
7.5
out of 10
Severity4_grave
Frequencyfrequent
Scope groups4
Detection difficulty4
🇫🇷 Définition (FR)
Tendance à rechercher, interpréter et mémoriser des informations qui confirment les croyances préexistantes.
🇬🇧 Definition (EN)
Tendency to search for, interpret, and recall information that confirms pre-existing beliefs.
TriAxis Taxonomy
Structural Classification
O
Origin
O3
Human-Cognitive
L
Lifecycle
L7
Deployment
S
Specific
S11
Confirmation bias
💡
Concrete Example
Un LLM renforce les impressions initiales erronées d'un clinicien au lieu de les remettre en question.
📊 Detection Metrics
Distribution ShiftDemographic Parity Difference
⚙ Alert Thresholds
Distribution Shift0.1
Demographic Parity Difference0.1
📚 Sources & Scientific References
- •Confirmation Bias: A Ubiquitous Phenomenon in Many GuisesNickerson, R.S. (1998)
- •Black-box Audit of YouTube's Video Recommendation: Investigation of Misinformation Filter Bubble Dynamics (Extended Abstract)Matus Tomlein, Branislav Pecher, Jakub Simko, Ivan Srba, Robert Moro, et al. (2022)
🛡 Impact & Mitigation
🎯 Vulnerable groups impacted
No specific groups.
🛠 Mitigation methodologies
- SHAP_GROUP : SHAP Group Analysis
- AUDIT_TIERS : Third-party Audit
🏢 Sectors concerned
Media & Social Platforms (Risk: /5)Healthcare & Medicine (Risk: /5)
⚖ Applicable regulations
🇪🇺 Europe
- •AI_ACT_14 : 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
4f918a1d-583a-45ee-ab46-e61aa84d24ae
Explore other biases
250 documented biases, classified by the TriAxis taxonomy.