Black-Box Visual Prompt Engineering for Mitigating Object Hallucination in Large Vision Language Models
Sangmin Woo, Kang Zhou, Yun Zhou, Shuai Wang, Sheng Guan, Haibo Ding, Lin Lee Cheong
Abstract
Large Vision Language Models (LVLMs) often suffer from object hallucination, which undermines their reliability. Surprisingly, we find that simple object-based visual prompting—overlaying visual cues (e.g., bounding box, circle) on images—can significantly mitigate such hallucination; however, different visual prompts (VPs) vary in effectiveness. To address this, we propose Black-Box Visual Prompt Engineering (BBVPE), a framework to identify optimal VPs that enhance LVLM responses without needing access to model internals. Our approach employs a pool of candidate VPs and trains a router model to dynamically select the most effective VP for a given input image. This black-box approach is model-agnostic, making it applicable to both open-source and proprietary LVLMs. Evaluations on benchmarks such as POPE and CHAIR demonstrate that BBVPE effectively reduces object hallucination.
BibTeX
@inproceedings{woo-etal-2025-black,
title = "Black-Box Visual Prompt Engineering for Mitigating Object Hallucination in Large Vision Language Models",
author = "Woo, Sangmin and
Zhou, Kang and
Zhou, Yun and
Wang, Shuai and
Guan, Sheng and
Ding, Haibo and
Cheong, Lin Lee",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-short.45/",
pages = "529--538",
ISBN = "979-8-89176-190-2"
}