IBI-001163_significativepublie
Format Preference Bias
Biais de préférence de format
IBI Score
6.5
out of 10
Severity3_significative
Frequencysystematique
Scope groups3
Detection difficulty3
🇫🇷 Définition (FR)
Modèles accordant de meilleures évaluations aux contenus formatés en Markdown ou listes.
🇬🇧 Definition (EN)
Models giving better evaluations to Markdown-formatted or bulleted content.
TriAxis Taxonomy
Structural Classification
O
Origin
O2
Computational & Statistical
L
Lifecycle
L6
Evaluation
S
Specific
S29
Presentation bias
💡
Concrete Example
Un juge LLM préfère une réponse en bullet points à une réponse en prose, même moins précise.
📊 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
- •Judging LLM-as-a-Judge with MT-Bench and Chatbot ArenaZheng, L., Chiang, W.-L., Sheng, Y., et al. (2023)
🛡 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
e52c80a8-a94c-45d8-af12-d2457a5cc6b6
Explore other biases
250 documented biases, classified by the TriAxis taxonomy.