arXiv cs.LG
· Papers
Guarantees on Dynamical System Distinguishability for LLM Token Generation
arXiv:2607.28667v1 Announce Type: new Abstract: Recent work has shown that classifying large language models (LLMs)' responses can be distinguished by modeling token embeddings as trajectories of a black-box dynamical system (DS) and comparing prediction residuals of two DSs. Despite the empirical success of this dynam