6 papers
Distinct dynamics of conceptual and referential disruptions in human reading and large language model processing
Rui He, Nihal Altay, Wolfram Hinzen
Linguistic meaning is grounded in conceptual content, from which reference to particular entities emerges as words enter discourse. To examine the processing dynamics associated wi…
The Changing Geometry of Grammar: Dimensionality and Neighborhood Reorganization across Transformer Layers
Samuele Vallisa, Federico Ravenda, Claudio Palominos +5
Transformer representations describe trajectories through high-dimensional vector spaces, which are shaped dynamically as tokens incorporate relational context across layers. Such…
Activation-Guided Neuron Intervention to Induce Alzheimer's-Related Computational Language Phenotypes in a Large Language Model
Rui He, Ercong Nie, Hong Jiang +3
Changes in spontaneous speech provide an early signal of cognitive dysfunction in Alzheimer's disease (AD) that large language models (LLMs) can detect. However, detection alone ca…
Linear-Time Global Visual Modeling without Explicit Attention
Ruize He, Dongchen Han, Gao Huang
Existing research largely attributes the global sequence modeling capability of Transformers to the explicit computation of attention weights, a process that inherently incurs quad…
The grip of grammar on meaning uncertainty: cross-linguistic evidence, neural correlates, and clinical relevance
Rui He, Claudio Palominos, Samuele Vallisa +16
Isolated word meanings are inherently uncertain. This uncertainty reduces when they are combined and anchored in context. We propose that grammar compresses meaning uncertainty cro…
Cross-lingual brain-language model alignment is robust but challenges hierarchical and computational accounts
Ni Yang, Rui He, Philipp Homan +3
Brain-language model alignment is often interpreted as evidence that transformer models implement computations similar to those of the human brain. This assumes that neural predict…