Mitigating style-image hallucination in large vision language models

• Main Author: He, Guoshun
• Other Authors: Alex Chichung Kot
• Format: Thesis-Master by Coursework
• Language: English
• Published: Nanyang Technological University 2025
• Subjects: Engineering; Out-of-domain; Hallucination; Lightweight model
• Online Access: https://hdl.handle.net/10356/182918
• Institution: Nanyang Technological University

LLMs are widely applied across various domains, yet a significant challenge remains—their performance deteriorates sharply in out-of-domain scenarios, often leading to increased hallucinations. Despite its importance, this phenomenon has received limited attention in academic research. To address this, we first construct a benchmark dataset using style transfer techniques and employ it to evaluate the out-of-domain performance of several popular large-scale models. Building upon these findings, we introduce CopeCap, a lightweight image captioning model that leverages collaborative prompting to achieve strong out-of-domain performance without requiring additional training.