Video Large Multimodal Models have achieved remarkable progress in video understanding, yet they remain prone to hallucinations, where generated responses are not faithfully supported by the input video. In this paper, we propose MultiToP, a multimodal-context-aware visual token patching framework that mitigates hallucinations by refining unreliable visual tokens before language generation. MultiToP introduces a lightweight Visual Token Patcher to predict token-level replacement distributions and selectively substitute unreliable visual tokens with a dynamic global patch token. To train the patcher effectively, we further propose information-guided rank calibration, which uses answer-conditioned frame-level information cues derived from the backbone to guide token replacement. Combined with ground-truth answer supervision and sparsity regularization, MultiToP enables localized visual evidence refinement without modifying the original model. Extensive experiments demonstrate that MultiToP effectively reduces hallucinations on Vript-HAL with negligible inference overhead, improving the F1 scores of Qwen3-VL-4B-Instruct by 50.60% over the vanilla model. Meanwhile, MultiToP preserves general video understanding ability, yielding an 18.58% relative accuracy gain on ActivityNet-QA for Video-LLaVA-7B.

翻译：视频大型多模态模型在视频理解领域取得了显著进展，但其生成的响应仍可能无法忠实地得到输入视频的支持，即存在幻觉问题。本文提出MultiToP，一种多模态上下文感知的视觉标记修补框架，通过在语言生成前优化不可靠的视觉标记来缓解幻觉。MultiToP引入轻量级视觉标记修补器（Visual Token Patcher），预测标记级替换分布并选择性地将不可靠的视觉标记替换为动态全局修补标记。为有效训练该修补器，我们进一步提出信息引导的秩校准方法，利用骨干网络导出的、基于答案的帧级信息线索来指导标记替换。结合真实答案监督与稀疏正则化，MultiToP实现了无需修改原始模型的局部化视觉证据优化。大量实验表明，MultiToP在Vript-HAL上有效降低了幻觉，且仅带来可忽略的推理开销——在Qwen3-VL-4B-Instruct上的F1分数较原始模型提升50.60%。同时，MultiToP保持通用视频理解能力，在ActivityNet-QA上为Video-LLaVA-7B带来18.58%的相对准确率提升。