Characterizing Large Language Model Geometry Solves Toxicity Detection and Generation
Published in arXiv Preprints, 2023
Large Language Models~(LLMs) drive current AI breakthroughs despite very little being known about their internal representations, e.g., how to extract a few informative features to solve various downstream tasks. To provide a practical and principled answer, we propose to characterize LLMs from a geometric perspective. Read more