3 papers
cs.CL2025
Token embeddings violate the manifold hypothesis
Michael Robinson, Sourya Dey, Tony Chiang
A full understanding of the behavior of a large language model (LLM) requires our grasp of its input token space. If this space differs from our assumptions, our comprehension of a…
math.DG2025
Probing the topology of the space of tokens with structured prompts
Michael Robinson, Sourya Dey, Taisa Kushner
This article presents a general and flexible method for prompting a large language model (LLM) to reveal its (hidden) token input embedding up to homeomorphism. Moreover, this arti…
math.DG2024
The structure of the token space for large language models
Michael Robinson, Sourya Dey, Shauna Sweet
Large language models encode the correlational structure present in natural language by fitting segments of utterances (tokens) into a high dimensional ambient latent space upon wh…