← all papers · overview

Representations Matter: Embedding Modes Of Large Language Models Using Dynamic Mode Decomposition

Abstract

Existing large language models (LLMs) are known for generating "hallucinated" content, namely a fabricated text of plausibly looking, yet unfounded, facts. To identify when these hallucination scenarios occur, we examine the properties of the generated text in the embedding space. Specifically, we draw inspiration from the dynamic mode decomposition (DMD) tool in analyzing the pattern evolution of

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).