Large language models place structured concepts on geometrically faithful manifolds: weekdays lie on a circle, months on another, usually taken to be a fixed world-model the network stores and looks up. We show that context is king: the structure a model actually uses is set by the in-context specification.
arXiv:2607. 10248v1 Announce Type: cross Abstract: Language builds discourse contexts other than the actual: a painting, a belief, a memory, a hypothetical.
By Oliver Steele, Jiangtao Wen, Yuxing Han
arXiv:2608. 13626v1 Announce Type: new Abstract: A hidden state signal can be decodable or causally usable without supporting a reusable action map.
By Dekun Yang
arXiv:2601. 11618v3 Announce Type: replace-cross Abstract: Neural architecture is often identified by module syntax, computation graphs, or the composite functions they realize.
By Luis F. Rosario Freytes (University of Michigan)
arXiv:2601. 06599v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) often encode whether a statement is true as a vector in their residual stream activations.
By Shivam Adarsh, Maria Maistro, Christina Lioma
arXiv:2608. 11797v1 Announce Type: new Abstract: Model merging by task arithmetic works until it doesn't, and the field diagnoses why with magnitudes: layerwise representation bias, deviations from cross-task linearity, parameter overlap.
By Chencheng Zhu