Answers are grounded in this paper and cite their sources.
This article demonstrates how structured prompts uncover token embedding topology in LLMs, suggesting insights into nonlinear autoregressive processes.
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 article provides strong theoretical justification -- a mathematical proof for generic LLMs -- for why this method should be expected to work. With this method in hand, we demonstrate its effectiveness by recovering the token subspace of Llemma-7B. The results of this paper apply not only to LLMs but also to general nonlinear autoregressive processes.
No takes yet. Share an insight, caveat, or question.
Robinson et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: