IBI-001114 - Severepublie
Contaminated Test Set Bias
Biais de test set contaminé
IBI Score
7.5
out of 10
Severity4_grave
Frequencyfrequent
Scope groups4
Detection difficulty4
🇫🇷 Définition (FR)
Données de test ayant fuité dans l'entraînement, gonflant artificiellement les performances.
🇬🇧 Definition (EN)
Test data that leaked into training, artificially inflating performance.
TriAxis Taxonomy
Structural Classification
O
Origin
O2
Computational & Statistical
L
Lifecycle
L6
Evaluation
S
Specific
S17
Measurement error bias
💡
Concrete Example
Des modèles LLM obtiennent des scores élevés sur des benchmarks dont les réponses sont dans les données d'entraînement.
📊 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
No specific groups.
🛠 Mitigation methodologies
- AUDIT_TIERS : Third-party Audit
🏢 Sectors concerned
Media & Social Platforms (Risk: /5)
⚖ Applicable regulations
🌍 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
d59d49a2-8efa-4168-b14d-c01cf4f85069
Explore other biases
250 documented biases, classified by the TriAxis taxonomy.