3 papers
cs.AI2026
Representational Curvature Modulates Behavioral Uncertainty in Large Language Models
Jack King, Evelina Fedorenko, Eghbal A. Hosseini
In autoregressive large language models (LLMs), temporal straightening offers an account of how the next-token prediction objective shapes representations. Models learn to progress…
cs.CL2026
Linear representations in language models can change dramatically over a conversation
Andrew Kyle Lampinen, Yuxuan Li, Eghbal Hosseini +2
Language model representations often contain linear directions that correspond to high-level concepts. Here, we study the dynamics of these representations: how representations evo…
cs.CL2026
Context Structure Reshapes the Representational Geometry of Language Models
Eghbal A. Hosseini, Yuxuan Li, Yasaman Bahri +2
Large Language Models (LLMs) have been shown to organize the representations of input sequences into straighter neural trajectories in their deep layers, which has been hypothesize…