Beyond One-Size-Fits-All: Multi-Domain, Multi-Task Framework for Embedding Model Selection

2024/03/30 by Khetan, Vivek
#Computation and Language (cs.CL) #FOS: Computer and information sciences #Information Retrieval (cs.IR)

paper · doi:10.48550/arxiv.2404.00458

Abstract

This position paper proposes a systematic approach towards developing a framework to help select the most effective embedding models for natural language processing (NLP) tasks, addressing the challenge posed by the proliferation of both proprietary and open-source encoder models.

Related

• LLMs are Also Effective Embedding Models: An In-depth Overview
• Prompt2Model: Generating Deployable Models from Natural Language Instructions
• Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond
• Language Models are Universal Embedders
• UER: An Open-Source Toolkit for Pre-training Models