Home›Biases›IBI-00096
IBI-000964 - Severepublie

LLM-as-a-Judge Bias

Biais d'évaluation par LLM

IBI Score
7.5
out of 10
Severity4_grave
Frequencyfrequent
Scope groups4
Detection difficulty4
🇫🇷 Définition (FR)

Biais introduits quand on utilise un LLM pour évaluer d'autres LLMs (préférence pour ses propres sorties).

🇬🇧 Definition (EN)

Bias introduced when using an LLM to evaluate other LLMs (preference for own outputs).

TriAxis Taxonomy

Structural Classification

O
Origin
O2
Computational & Statistical
L
Lifecycle
L6
Evaluation
S
Specific
S28
Interaction bias
💡
Concrete Example

GPT-4 préfère les réponses générées par GPT-4 dans les benchmarks comparatifs.

📊 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

🇪🇺 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
3c522d71-a675-4e61-b850-22925c02fce3

Explore other biases

250 documented biases, classified by the TriAxis taxonomy.