# When Text Hijacks Vision: Benchmarking and Mitigating Text Overlay-Induced Hallucination in Vision Language Models

arXiv: https://arxiv.org/abs/2604.17375 · HTML: https://mlsanity.com/paper/2604.17375/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 34 of its 67 references that are in the map.
- First posted on arXiv 19 Apr 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Hallucination mitigation in LVLMs](https://mlsanity.com/mllm/hallucination-mitigation-in-lvlms/)

## Builds on (most cited first, 30 of 34)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2311.16922/) (2023)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [LVBench: An Extreme Long Video Understanding Benchmark](https://mlsanity.com/paper/2406.08035/) (2024)
- [TempCompass: Do Video LLMs Really Understand Videos?](https://mlsanity.com/paper/2403.00476/) (2024)
- [Video Understanding with Large Language Models: A Survey](https://mlsanity.com/paper/2312.17432/) (2023)
- [MetaMorph: Multimodal Understanding and Generation via Instruction Tuning](https://mlsanity.com/paper/2412.14164/) (2024)
- [MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding](https://mlsanity.com/paper/2406.14515/) (2024)
- [TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document](https://mlsanity.com/paper/2403.04473/) (2024)
- [Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition](https://mlsanity.com/paper/2501.03230/) (2024)
- [Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review](https://mlsanity.com/paper/2403.02469/) (2024)
- [VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents](https://mlsanity.com/paper/2507.04590/) (2025)
- [TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models](https://mlsanity.com/paper/2410.10818/) (2024)
- [VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models](https://mlsanity.com/paper/2406.16338/) (2024)
- [VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding](https://mlsanity.com/paper/2412.03735/) (2024)
- [LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding](https://mlsanity.com/paper/2501.08282/) (2025)
- [Deep Reinforcement Learning from Policy-Dependent Human Feedback](https://mlsanity.com/paper/1902.04257/) (2019)
- [VCA: Video Curious Agent for Long Video Understanding](https://mlsanity.com/paper/2412.10471/) (2024)
- [eP-ALM: Efficient Perceptual Augmentation of Language Models](https://mlsanity.com/paper/2303.11403/) (2023)
- [Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought](https://mlsanity.com/paper/2505.23766/) (2025)
- [Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation](https://mlsanity.com/paper/2503.19622/) (2025)
- [VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation](https://mlsanity.com/paper/2411.13281/) (2024)
- [MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios](https://mlsanity.com/paper/2505.21333/) (2025)
- [Parrot Captions Teach CLIP to Spot Text](https://mlsanity.com/paper/2312.14232/) (2023)
- [VTimeCoT: Thinking by Drawing for Video Temporal Grounding and Reasoning](https://mlsanity.com/paper/2510.14672/) (2025)
- [Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object Perception](https://mlsanity.com/paper/2504.20468/) (2025)

## Abstract (arXiv)

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.