Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs

arXiv:2403.11755v1 Announce Type: cross
Abstract: Prompt ensembling of Large Language Model (LLM) generated category-specific prompts has emerged as an effective method to enhance zero-shot recognition ability of Vision-Language Models (VLMs). To obtain these category-specific prompts, the present methods rely on hand-crafting the prompts to the LLMs for generating VLM prompts for the downstream tasks. However, this requires manually composing these task-specific prompts and still, they might not cover the diverse set of visual concepts and task-specific styles associated with the …

abstract arxiv cs.ai cs.cv cs.lg generated language language model language models large language large language model llm llms meta prompt prompting prompts recognition type vision vision-language models visual vlm vlms zero-shot