IBI-001144 - Severepublie
Misinterpretation Bias
Biais de mauvaise interprétation
IBI Score
7.5
out of 10
Severity4_grave
Frequencyfrequent
Scope groups4
Detection difficulty4
🇫🇷 Définition (FR)
Interprétation erronée par l'utilisateur des sorties d'un système d'IA, souvent par excès de confiance.
🇬🇧 Definition (EN)
User misinterpretation of AI system outputs, often due to overconfidence.
TriAxis Taxonomy
Structural Classification
O
Origin
O3
Human-Cognitive
L
Lifecycle
L7
Deployment
S
Specific
S29
Presentation bias
💡
Concrete Example
Un juge interprète un score COMPAS de 0,7 comme « 70% de probabilité de récidive ».
📊 Detection Metrics
Distribution ShiftDemographic Parity Difference
⚙ Alert Thresholds
Distribution Shift0.1
Demographic Parity Difference0.1
📚 Sources & Scientific References
- •The Mythos of Model InterpretabilityLipton, Z.C. (2018)
- •Google translates doctor's orders into Spanish and Chinese with few significant errors (ScienceDaily, communiqu� UCSF ; �tude : Assessing the Use of Google Translate for Spanish and Chinese Translations of Emergency Department Discharge Instructions, JAMA Internal Medicine)Elaine C. Khoong, Eric Steinbrook, Cortlyn Brown, Alicia Fernandez (UCSF) (2019)
🛡 Impact & Mitigation
⚠ Documented evidence (Studies & Incidents)
- AI's 'insane' translation mistakes endanger US asylum cases : Source : https://www.context.news:443/ai/ais-insane-translation-mistakes-endanger-us-asylum-cases
Impact:
🎯 Vulnerable groups impacted
No specific groups.
🛠 Mitigation methodologies
- AUDIT_TIERS : Third-party Audit
🏢 Sectors concerned
Justice & Security (Risk: /5)Healthcare & Medicine (Risk: /5)
⚖ Applicable regulations
🇪🇺 Europe
- •AI_ACT_13 : 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
f379c986-d28e-4bcc-b3c2-77d487d20cc0
Explore other biases
250 documented biases, classified by the TriAxis taxonomy.