Creative4U: MLLMs-based Advertising Creative Image Selector with Comparative Reasoning

TL;DR

This paper introduces Creative4U, a novel MLLMs-based system for explainable creative image assessment and selection in advertising, utilizing a new dataset and advanced reasoning techniques to improve accuracy and interpretability.

Contribution

It presents the first explainable creative assessment paradigm, a new dataset CreativePair, and a creative selector model that integrates comparative reasoning with user interests.

Findings

Creative4U achieves high accuracy in image selection.

The approach outperforms existing methods in both offline and online tests.

The dataset and code are publicly available for further research.

Abstract

Creative image in advertising is the heart and soul of e-commerce platform. An eye-catching creative image can enhance the shopping experience for users, boosting income for advertisers and advertising revenue for platforms. With the advent of AIGC technology, advertisers can produce large quantities of creative images at minimal cost. However, they struggle to assess the creative quality to select. Existing methods primarily focus on creative ranking, which fails to address the need for explainable creative selection. In this work, we propose the first paradigm for explainable creative assessment and selection. Powered by multimodal large language models (MLLMs), our approach integrates the assessment and selection of creative images into a natural language generation task. To facilitate this research, we construct CreativePair, the first comparative reasoning-induced creative dataset featuring 8k annotated image pairs, with each sample including a label indicating which image is superior. Additionally, we introduce Creative4U (pronounced Creative for You), a MLLMs-based creative selector that takes into account users' interests. Through Reason-to-Select RFT, which includes supervised fine-tuning with Chain-of-Thought (CoT-SFT) and Group Relative Policy Optimization (GRPO) based reinforcement learning, Creative4U is able to evaluate and select creative images accurately. Both offline and online experiments demonstrate the effectiveness of our approach. Our code and dataset will be made public to advance research and industrial applications.