SOURCE-LINKED INTELLIGENCE

Distribution-aware Language Neuron Identification in Multilingual Large Language Models

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Multilingual large language models (mLLMs) contain a small fraction of feed-forward neurons that are sensitive to particular languages, commonly termed language-specific neurons. Existing work measures language specificity using the entropy of each neuron's language-wise probabilities of being active, where a neuron is considered active when its activation value is positive. However, this approach may not fully capture the multilingual nature of mLLMs, where language representations are distributional and mutually related. We propose Distribution-aware Language Neuron selection, which leverage

Read original source ↗ Open in workspace

recordType

paper

region

Global