Auditing LLM Bias (BERT/XLM-R) for EU AI Act Compliance. Measuring Statistical Parity and Algorithmic Fairness in Multilingual settings
-
Updated
Jan 10, 2026 - Jupyter Notebook
#
nlp-bias
Here are 3 public repositories matching this topic...
Probed gender-science bias in transformer language models by implementing WEAT on English and Urdu embeddings. Conducted comparative evaluation across BERT, RoBERTa, DistilBERT, and XLM-RoBERTa, revealing model and language-dependent bias patterns and providing reproducible benchmarks.
natural-language-processing bias-detection algorithmic-bias machine-learning-research contextual-embeddings ethical-ai language-model-evaluation multilingual-nlp nlp-bias transformer-bias weat-bias-analysis cross-lingual-fairness fairness-in-nlp
-
Updated
Feb 21, 2026 - Jupyter Notebook
🛡️ Framework de défense contre le Vandalisme Cognitif et l'empoisonnement de données dans les LLMs. Analyse quantitative du révisionnisme historique, métriques de dérive morale et implémentation de preuves de réalité par hachage temporel (C2PA/Blockchain)
devsecops adversarial-machine-learning cognitive-security ai-ethics ai-alignment data-poisoning c2pa information-warfare llm-security model-collapse lichen-universe disinformation-defense lichen-collectives nlp-bias bryan-ouellette historical-revisionism blockchain-provenance grokipedia-analysis epistemic-security truth-anchoring
-
Updated
Jan 29, 2026
Improve this page
Add a description, image, and links to the nlp-bias topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the nlp-bias topic, visit your repo's landing page and select "manage topics."