Black-Box Visual Prompt Engineering for Mitigating Object Hallucination in Large Vision Language Models
This addresses reliability issues in LVLMs for users in vision-language tasks, but it is incremental as it builds on existing visual prompting methods.
The paper tackles object hallucination in Large Vision Language Models (LVLMs) by proposing Black-Box Visual Prompt Engineering (BBVPE), a framework that uses a router model to select optimal visual prompts, and demonstrates its effectiveness in reducing hallucination on benchmarks like POPE and CHAIR.
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.