IBI-000954 - Severepublie
LLM Self-Evaluation Bias
Biais d'auto-évaluation LLM
IBI Score
8.0
out of 10
Severity4_grave
Frequencysystematique
Scope groups4
Detection difficulty4
🇫🇷 Définition (FR)
LLMs s'auto-évaluant favorablement par rapport à d'autres modèles.
🇬🇧 Definition (EN)
LLMs self-evaluating favorably compared to other models.
TriAxis Taxonomy
Structural Classification
O
Origin
O2
Computational & Statistical
L
Lifecycle
L6
Evaluation
S
Specific
S28
Interaction bias
💡
Concrete Example
GPT-4 s'attribue des scores plus élevés que ses concurrents dans des benchmarks auto-évalués.
📊 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
- •LLM Evaluators Recognize and Favor Their Own GenerationsArjun Panickssery, Samuel R. Bowman, Shi Feng (2024)
- •
🛡 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
8015d47d-7237-46ff-84fa-7a5d8b16f3ce
Explore other biases
250 documented biases, classified by the TriAxis taxonomy.