Balance, Don’t Boost: Calibrating Visual Evidence to Reduce Omissions without Fabrications

Guangzong Si, Hao Yin, Xianfei Li, Qing Ding, Wenlong Liao, Tao He, Pai Peng, Wentao Zhu

Keywords: Hallucinations, MLLMs, LVLMs

TL;DR: This paper introduce a plug-and-play hallucination mitigation method.

Abstract: Multimodal Large Language Models (MLLMs) have achieved impressive advances, yet object hallucination remains a persistent challenge. Existing methods, based on the flawed assumption that omission and fabrication hallucinations share a common cause, often reduce omissions only to trigger more fabrications. In this work, we overturn this view by demonstrating that omission hallucinations arise from insufficient confidence when mapping perceived visual features to linguistic expressions, whereas fabrication hallucinations result from spurious associations within the cross-modal representation space due to statistical biases in the training corpus. Building on findings from visual attention intervention experiments, we propose the Visual-Semantic Attention Potential Field, a conceptual framework that reveals how the model constructs visual evidence to infer the presence or absence of objects. Leveraging this insight, we introduce Visual Potential Field Calibration (VPFC), a plug-and-play hallucination mitigation method that effectively reduces omission hallucinations without introducing additional fabrication hallucinations. Our findings reveal a critical oversight in current object hallucination research and chart new directions for developing more robust and balanced hallucination mitigation strategies.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 6550