Meta-Task Prompting Elicits Embeddings from Large Language Models

Authors:
  • YLYibin Lei
    Yibin Lei
  • DWDi Wu
    Di Wu
  • TZTianyi Zhou
    Tianyi Zhou
  • TSTao Shen
    Tao Shen
  • YCYu Cao
    Yu Cao
  • CTChongyang Tao
    Chongyang Tao
  • AYAndrew Yates
    Andrew Yates

Abstract
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.