IBI-000873_significativepublie
Differential Politeness Bias
Biais de politesse différenciée
IBI Score
6.3
out of 10
Severity3_significative
Frequencyfrequent
Scope groups3
Detection difficulty4
🇫🇷 Définition (FR)
LLMs adoptant des tons différents selon le groupe démographique perçu de l'utilisateur.
🇬🇧 Definition (EN)
LLMs adopting different tones based on perceived demographic group of the user.
TriAxis Taxonomy
Structural Classification
O
Origin
O3
Human-Cognitive
L
Lifecycle
L7
Deployment
S
Specific
S28
Interaction bias
💡
Concrete Example
Un LLM utilise un ton plus formel avec les utilisateurs supposés occidentaux et familier avec les autres.
📊 Detection Metrics
Distribution ShiftDemographic Parity Difference
⚙ Alert Thresholds
Distribution Shift0.1
Demographic Parity Difference0.1
📚 Sources & Scientific References
- •Bias and Fairness in Large Language Models: A SurveyIsabel O. Gallegos, Ryan A. Rossi, Joe Barrow, Md Mehrab Tanjim, Sungchul Kim, Franck Dernoncourt, Tong Yu, Ruiyi Zhang, Nesreen K. Ahmed (2024)
- •Evaluating the Impact of Racial Cues on MLLMs Judgements of Politeness and OffensivenessMahammed Kamruzzaman, Gene Louis Kim (2025)
🛡 Impact & Mitigation
🎯 Vulnerable groups impacted
Minority language speakersBlack / Afro-descendant
🛠 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
ade38c70-6239-42f9-99b0-04c92b849f54
Explore other biases
250 documented biases, classified by the TriAxis taxonomy.