Meta-Task Prompting Elicits Embeddings from Large Language Models
This provides a resource-efficient embedding method for natural language processing applications, though it appears incremental as it builds on existing prompting techniques.
The paper tackles the problem of generating high-quality sentence embeddings from Large Language Models without fine-tuning by introducing MetaEOL, a method using meta-task prompting with explicit one-word limitations, which achieves competitive performance on Semantic Textual Similarity benchmarks and excels in downstream tasks, surpassing contrastive-trained models.
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.