Meta-Task Prompting Elicits Embeddings from Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lei, Yibin, Wu, Di, Zhou, Tianyi, Shen, Tao, Cao, Yu, Tao, Chongyang, Yates, Andrew
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911962953154560
author Lei, Yibin
Wu, Di
Zhou, Tianyi
Shen, Tao
Cao, Yu
Tao, Chongyang
Yates, Andrew
author_facet Lei, Yibin
Wu, Di
Zhou, Tianyi
Shen, Tao
Cao, Yu
Tao, Chongyang
Yates, Andrew
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_18458
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Meta-Task Prompting Elicits Embeddings from Large Language Models
Lei, Yibin
Wu, Di
Zhou, Tianyi
Shen, Tao
Cao, Yu
Tao, Chongyang
Yates, Andrew
Computation and Language
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.
title Meta-Task Prompting Elicits Embeddings from Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2402.18458