← all papers · overview

Unraveling Babel: Exploring Multilingual Activation Patterns Of Llms And Their Applications

Abstract

Recently, large language models (LLMs) have achieved tremendous breakthroughs in the field of NLP, but still lack understanding of their internal neuron activities when processing different languages. We designed a method to convert dense LLMs into fine-grained MoE architectures, and then visually studied the multilingual activation patterns of LLMs through expert activation frequency heatmaps. Th

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).