When Text Hijacks Vision: Benchmarking and Mitigating Text Overlay-Induced Hallucination in Vision Language Models
Recent advances in Vision-Language Models (VLMs) have substantially enhanced their ability across multimodal video understanding benchmarks spanning temporal, action, object, and spatial understanding. However, we identify a critical yet overlooked issue: when embedded on-screen text contradicts the visual scene, existing VLMs systematically hallucinate, prioritizing overlay textual semantics over the actual visual content. We define this phenomenon as Text Overlay-Induced Hallucination (TOIH). In this work, we propose VisualTextTrap, the first comprehensive benchmark, including large-scale human-validated samples with specifically designed evaluation metrics. In particular, we construct VisualTextTrap from widely-used public datasets using a scalable hybrid pipeline of VLMs assisted text generation and rigorous manual verification. The benchmark features 6,057 samples annotated across 88 fine-grained attributes within four dimensions, with hallucination intensity quantified on a five-level scale (L1--L5) that reflects the semantic contradiction between overlay text and visual reality. Moreover, we propose Visual Text Hallucination Mitigation Mixture-of-Experts (VTHM-MoE), a novel Vision-Text Disentanglement framework that employs a dual-encoder architecture. Concretely, four dimension-specialized expert modules spanning Temporal, Action, Object, and Spatial reasoning are first pre-trained to identify and leverage cross-modal discrepancies between textual semantics and actual video content. We develop an Adaptive Token Routing Strategy to enable dynamic expert allocation, conferring robust resistance to TOIH while preserving performance on uncontaminated videos. Extensive experiments conducted on our VisualTextTrap benchmark verify the effectiveness of VTHM-MoE, outperforming state-of-the-art counterparts with diverse video question answering tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Video Question AnsweringSpatial ReasoningText GenerationSimilar Papers 제목 키워드 기반
Image Hijacks: Adversarial Images can Control Generative Models at Runtime
Are foundation models secure against malicious actors? In this work, we focus on the image input to a vision-language model (VLM). We discover image hijacks, adversarial images that control the behaviour of VLMs at infer…
Language ModelingLanguage ModellingA Study of the Attention Abnormality in Trojaned BERTs
Trojan attacks raise serious security concerns. In this paper, we investigate the underlying mechanism of Trojaned BERT models. We observe the attention focus drifting behavior of Trojaned models, i.e., when encountering…
A Study of the Attention Abnormality in Trojaned BERTs
Trojan attacks raise serious security concerns. In this paper, we investigate the underlying mechanism of Trojaned BERT models. We observe the attention focus drifting behavior of Trojaned models, i.e., when encountering…
SDGBiasBench: Benchmarking and Mitigating Vision--Language Models' Biases in Sustainable Development Goals
Assessing progress toward the Sustainable Development Goals (SDGs) requires multi-step reasoning over visual cues, contextual knowledge, and development indicators, where incomplete evidence use and imperfect evidence in…
SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision
Large Vision-Language Models (LVLMs) recently achieve significant breakthroughs in understanding complex visual-textual contexts. However, hallucination issues still limit their real-world applicability. Although previou…
Scene Understanding