Danial Namazifard
@namazifard.bsky.social
NLP Graduate Researcher at The University of Tehran #NLProc
To enable this, we introduce MUREL, an 85.2M-token multicultural resource, and a comprehensive pipeline to separate language- vs. culture-related neurons and assess their roles via targeted ablations.
Grateful to @lukasgalke.bsky.social for his guidance and support!
Grateful to @lukasgalke.bsky.social for his guidance and support!
September 5, 2025 at 1:20 PM
To enable this, we introduce MUREL, an 85.2M-token multicultural resource, and a comprehensive pipeline to separate language- vs. culture-related neurons and assess their roles via targeted ablations.
Grateful to @lukasgalke.bsky.social for his guidance and support!
Grateful to @lukasgalke.bsky.social for his guidance and support!
We study how cultural information is represented inside multilingual LLMs by localizing and intervening on neuron subsets across four models and six cultures, including English, German, Danish, Chinese, Russian, and Persian.
September 5, 2025 at 1:20 PM
We study how cultural information is represented inside multilingual LLMs by localizing and intervening on neuron subsets across four models and six cultures, including English, German, Danish, Chinese, Russian, and Persian.