When Dimensionality Hurts: The Role of LLM Embedding Compression for Noisy Regression Tasks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Drinkall, Felix, Pierrehumbert, Janet B., Zohren, Stefan
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Computational Engineering, Finance, and Science Machine Learning Computational Finance
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.02199