paper-with-me

홈 › Papers

HIVE: Understanding Post-Hallucination Reasoning in Vision Language Models

2026-07-08 · Feng He, Zhenting Wang, Qifan Wang, Qiang Guan, Dongfang Liu, Ruixiang Tang, Qiankun Li arxiv

Hallucinations in vision language models (VLMs) are commonly treated as semantic errors, yet they often arise from partial or ambiguous visual evidence. Prior work mainly focuses on detecting or suppressing hallucinations at generation time, leaving the subsequent reasoning stage largely unexplored. In this work, we study Post Hallucination Reasoning (PHR), the stage in which hallucinated semantics enter the model's inference context and influence downstream predictions. To systematically investigate PHR, we introduce HIVE, Hallucination Inference and Verification Engine, an evaluation infrastructure that enables controlled comparisons between faithful and hallucinated captions. Across nine tasks and nine models, we observe structured modality dependent patterns: hallucinated captions often improve accuracy on vision language tasks, while text only tasks exhibit limited or unstable effects. Further analyses show that hallucinated cues broaden semantic coverage and reshape reasoning dynamics while preserving stable inference. These findings highlight that hallucinated semantics may influence downstream reasoning once they enter the model's inference context. Understanding this post hallucination stage is important for improving the reliability and interpretability of multimodal reasoning systems. Code is publicly available at https://github.com/hefengcs/HIVE.

📄 PDF Abstract BibTeX arXiv:2607.07507

Code (0)

등록된 구현이 없습니다.

Tasks

Multimodal Reasoning

Similar Papers 제목 키워드 기반

Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models

2026-04-03 · Gengwei Zhang, Jie Peng, Zhen Tan, Mufan Qiu 외 arxiv

The recent success of reinforcement learning (RL) in large reasoning models has inspired the growing adoption of RL for post-training Multimodal Large Language Models (MLLMs) to enhance their visual reasoning capabilitie…

Reinforcement LearningMultimodal ReasoningVisual Reasoning

Are Reasoning Models More Prone to Hallucination?

2025-05-29 · Zijun Yao, Yantao Liu, Yanxu Chen, Jianhui Chen 외

Recently evolved large reasoning models (LRMs) show powerful performance in solving complex tasks with long chain-of-thought (CoT) reasoning capability. As these LRMs are mostly developed by post-training on formal reaso…

Hallucination

Decoupling Perception from Reasoning for Hallucination-Resistant Video Understanding

2025-11-23 · Bowei Pu, Chuanbin Liu, Yifan Ge, Peicheng Zhou 외 arxiv

Video Large Language Models improve reasoning over complex videos by generating intermediate reasoning text. However, reliable reasoning depends on accurate video perception. In existing approaches, perception evidence i…

Analyzing and Mitigating Object Hallucination in Large Vision-Language Models

2023-10-01 · Yiyang Zhou, Chenhang Cui, Jaehong Yoon, Linjun Zhang 외

Large vision-language models (LVLMs) have shown remarkable abilities in understanding visual information with human languages. However, LVLMs still suffer from object hallucination, which is the problem of generating des…

HallucinationHallucination EvaluationObjectObject Hallucination

Multimodal Latent Reasoning via Hierarchical Visual Cues Injection

2026-02-05 · Yiming Zhang, Qiangyu Yan, Borui Jiang, Kai Han arxiv

The advancement of multimodal large language models (MLLMs) has enabled impressive perception capabilities. However, their reasoning process often remains a "fast thinking" paradigm, reliant on end-to-end generation or e…