Scaling Sentence Embeddings with Large Language Models

Ting Jiang, Shaohan Huang, Zhongzhi Luan, Deqing Wang, Fuzhen Zhuang


Abstract
Large Language Models (LLMs) have recently gained significant interest due to their impressive results in various natural language tasks. However, their application to sentence embeddings is still under active research. In this work, we introduce PromptEOL, a simple and efficient method designed to enhance LLM performance on sentence embeddings with a one-word limitation. We further integrate PromptEOL with in-context learning and alignment to leverage LLMs in two settings: without fine-tuning and with fine-tuning. Our extensive experiments show that PromptEOL enables LLMs to generate superior sentence embeddings without fine-tuning, outperforming contrastive learning methods. Additionally, with fine-tuning, a 2.7B parameter model using PromptEOL surpasses the performance of a 4.8B parameter model from previous methods. We also analyze how scaling model parameters, from 125 million to 66 billion, impacts sentence embedding performance.
Anthology ID:
2024.findings-emnlp.181
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3182–3196
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.181
DOI:
Bibkey:
Cite (ACL):
Ting Jiang, Shaohan Huang, Zhongzhi Luan, Deqing Wang, and Fuzhen Zhuang. 2024. Scaling Sentence Embeddings with Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 3182–3196, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Scaling Sentence Embeddings with Large Language Models (Jiang et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.181.pdf
Software:
 2024.findings-emnlp.181.software.zip