TopoLM: brain-like spatio-functional organization in a topographic language model
This work addresses the unclear mechanisms of functional organization in the brain's language system, providing a model that aligns with empirical observations, though it builds on existing work from vision literature.
The authors tackled the problem of understanding the mechanisms behind the spatial organization of neurons in the brain's language system by developing TopoLM, a transformer language model with a two-dimensional spatial representation. The result was that TopoLM successfully predicted the emergence of spatio-functional clusters matching those observed in human cortex, suggesting a unified spatial objective drives this organization.
Neurons in the brain are spatially organized such that neighbors on tissue often exhibit similar response profiles. In the human language system, experimental studies have observed clusters for syntactic and semantic categories, but the mechanisms underlying this functional organization remain unclear. Here, building on work from the vision literature, we develop TopoLM, a transformer language model with an explicit two-dimensional spatial representation of model units. By combining a next-token prediction objective with a spatial smoothness loss, representations in this model assemble into clusters that correspond to semantically interpretable groupings of text and closely match the functional organization in the brain's language system. TopoLM successfully predicts the emergence of the spatio-functional organization of a cortical language system as well as the organization of functional clusters selective for fine-grained linguistic features empirically observed in human cortex. Our results suggest that the functional organization of the human language system is driven by a unified spatial objective, and provide a functionally and spatially aligned model of language processing in the brain.