We introduce a new unsupervised text embedding method, Meta-Task Prompting with Explicit One-Word Limitation (MetaEOL), for generating high-quality sentence embeddings from Large Language Models (LLMs) without the need for model fine-tuning. Leveraging meta-task prompting, MetaEOL guides LLMs to produce embeddings through a series of carefully designed prompts that address multiple representational aspects. Our comprehensive experiments demonstrate that embeddings averaged from various meta-tasks are versatile embeddings that yield competitive performance on Semantic Textual Similarity (STS) benchmarks and excel in downstream tasks, surpassing contrastive-trained models. Our findings suggest a new scaling law, offering a versatile and resource-efficient approach for embedding generation across diverse scenarios.
@article{arxiv.2402.18458,
title = {Meta-Task Prompting Elicits Embeddings from Large Language Models},
author = {Yibin Lei and Di Wu and Tianyi Zhou and Tao Shen and Yu Cao and Chongyang Tao and Andrew Yates},
journal= {arXiv preprint arXiv:2402.18458},
year = {2024}
}