Metadata
- Authors: Eric Tang Bangding Yang Xingyou Song
- Full Title:: Understanding LLM Embeddings for Regression
- Category:: 🗞️Articles
- URL:: https://arxiv.org/pdf/2411.14708
- Finished date:: 2024-11-26
Highlights
LLM embeddings as features can be better for high-dimensional regression tasks than using traditional feature engineering. This regression performance can be explained in part due to LLM embeddings over numeric data inherently preserving Lipschitz continuity over the feature space. (View Highlight)