CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Black-Box Vision-Language Models

Jul 17, 2026

Researchers introduce CARPRT, a training-free method that assigns class-specific weights to prompts for zero-shot image classification using vision-language models. Unlike previous approaches that use the same prompt weights for all classes, CARPRT captures dependencies between prompts and class labels, leading to improved classification accuracy. The method is evaluated on standard benchmarks and shows superior performance over class-independent reweighting. Code is available on GitHub.

Why it matters: CARPRT addresses a key limitation in zero-shot image classification by modeling prompt-class dependencies, resulting in more accurate predictions.

Full story at: arXiv Machine Learning ↗