Work

Retrieval Visual Contrastive Decoding to Mitigate Object Hallucinations in Large Vision-Language Models

Year: 2025

Type: conference-paper

Abstract: Despite significant advancements in Large Vision-Language Models, Object Hallucination (OH) remains a persistent challenge.Building upon prior studies on contrastive decoding that address this issue without requiring additional model training, we introduce RVCD (Retrieval Visual Contrastive Decoding), an advanced method to suppress OH.RVCD leverages both negative and positive images at the logit level, explicitly referencing AI-generated images designed to represent a single concept.Our approach demonstrates substantial improvements over existing decoding-based methods.

DOI: 10.18653/v1/2025.findings-acl.430

Authors: Jihoon Lee, Min Song

Institution: Yonsei University

Language: English

Topic: Multimodal Machine Learning Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold