Whitening Not Recommended for Classification Tasks in LLMs
Computation and Language
2024-07-19 v1 Artificial Intelligence
Machine Learning
Abstract
Sentence embedding is a cornerstone in NLP. Whitening has been claimed to be an effective operation to improve embedding quality obtained from Large Language Models (LLMs). However, we find that the efficacy of whitening is model-dependent and task-dependent. In particular, whitening degenerates embeddings for classification tasks. The conclusion is supported by extensive experiments. We also explored a variety of whitening operations, including PCA, ZCA, PCA-Cor, ZCA-Cor and Cholesky whitenings. A by-product of our research is embedding evaluation platform for LLMs called SentEval+.
Cite
@article{arxiv.2407.12886,
title = {Whitening Not Recommended for Classification Tasks in LLMs},
author = {Ali Forooghi and Shaghayegh Sadeghi and Jianguo Lu},
journal= {arXiv preprint arXiv:2407.12886},
year = {2024}
}