Year: 2025
Type: preprint
Abstract: Large language models struggle with representing and generating rare tokens despite their importance in specialized domains. In this study, we identify neuron structures with exceptionally strong influence on language model's prediction of rare tokens, termed as rare token neurons, and investigate the mechanism for their emergence and behavior. These neurons exhibit a characteristic three-phase organization (plateau, power-law, and rapid decay) that emerges dynamically during training, evolving from a homogeneous initial state to a functionally differentiated architecture. In the activation space, rare token neurons form a coordinated subnetwork that selectively co-activates while avoiding co-activation with other neurons. This functional specialization potentially correlates with the development of heavy-tailed weight distributions, suggesting a statistical mechanical basis for emergent specialization.
Source: arXiv (Cornell University)
Authors: Liu, Jing, Wang, Haozheng, Li, Yueheng
Institutions: Centre National de la Recherche Scientifique, Université Paris Sciences et Lettres, École Normale Supérieure - PSL, École des hautes études en sciences sociales, Université Paris Cité, Sorbonne Université, Sorbonne Paris Cité, École Normale Supérieure, Laboratoire de Physique de l'Ecole Normale Supérieure
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4417302244
Cites:
Cited by:
Related to: