BannerBench: Benchmarking Vision Language Models for Multi-Ad Selection with Human Preferences

Hiroto Otake, Peinan Zhang, Yusuke Sakai, Masato Mita, Hiroki Ouchi, Taro Watanabe


Abstract
Web banner advertisements, which are placed on websites to guide users to a targeted landing page (LP), are still often selected manually because human preferences are important in selecting which ads to deliver. To automate this process, we propose a new benchmark, BannerBench, to evaluate the human preference-driven banner selection process using vision-language models (VLMs). This benchmark assesses the degree of alignment with human preferences in two tasks: a ranking task and a best-choice task, both using sets of five images derived from a single LP. Our experiments show that VLMs are moderately correlated with human preferences on the ranking task. In the best-choice task, most VLMs perform close to chance level across various prompting strategies. These findings suggest that although VLMs have a basic understanding of human preferences, most of them struggle to pinpoint a single suitable option from many candidates.
Anthology ID:
2025.findings-emnlp.1311
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
24145–24159
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.1311/
DOI:
Bibkey:
Cite (ACL):
Hiroto Otake, Peinan Zhang, Yusuke Sakai, Masato Mita, Hiroki Ouchi, and Taro Watanabe. 2025. BannerBench: Benchmarking Vision Language Models for Multi-Ad Selection with Human Preferences. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 24145–24159, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
BannerBench: Benchmarking Vision Language Models for Multi-Ad Selection with Human Preferences (Otake et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.1311.pdf
Checklist:
 2025.findings-emnlp.1311.checklist.pdf