IBI-000904 - Severepublie
In-Context Learning Bias
Biais d'apprentissage en contexte
IBI Score
7.5
out of 10
Severity4_grave
Frequencyfrequent
Scope groups4
Detection difficulty4
🇫🇷 Définition (FR)
Modèles apprenant des biais à partir d'exemples fournis dans le contexte.
🇬🇧 Definition (EN)
Models learning biases from examples provided in the context.
TriAxis Taxonomy
Structural Classification
O
Origin
O2
Computational & Statistical
L
Lifecycle
L7
Deployment
S
Specific
S28
Interaction bias
💡
Concrete Example
Un LLM apprend un biais racial à partir de 5 exemples fournis dans le prompt.
📊 Detection Metrics
Distribution ShiftDemographic Parity Difference
⚙ Alert Thresholds
Distribution Shift0.1
Demographic Parity Difference0.1
📚 Sources & Scientific References
- •Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. (2020)
- •Transformers with Endogenous In-Context Learning: Bias Characterization and MitigationHaotian Wang, Hao Zou, Haoxuan Li, Haoang Chi, Yang Shi, Yuanxing Zhang, Wenjing Yang, Xinwang Liu, Zhouchen Lin (2026)
🛡 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
b9cc34ab-7eee-4a60-b8b8-4e49a60eb587
Explore other biases
250 documented biases, classified by the TriAxis taxonomy.