Large Vision-Language Models (LVLMs) have achieved impressive progress in multimodal reasoning, yet they remain prone to object hallucinations, generating descriptions of objects that are not present in the input image. In this work, we investigate hallucination from the perspective of attention-value dynamics inside LVLM vision encoders. We identify a consistent three-phase structure of visual processing---diffusion, focus, and rediffusion---and show that the focus phase is where attention most clearly separates strongly and weakly supported visual tokens. However, low attention does not necessarily imply negligible downstream influence: low-attention tokens in the focus phase can still exert non-negligible value-side influence on the attention output relative to their small attention mass. Through controlled phase-wise value interventions, we find that hallucination behavior is particularly sensitive to the value content of low-attention tokens during this phase. Replacing or neutralizing these values reduces hallucination metrics while largely preserving grounded object evidence. A token-level teacher-forcing analysis further shows that the intervention reduces the probability of hallucinated object tokens with much smaller effects on ground-truth object tokens. In addition, Visual Attention Ratio (VAR) analysis shows that focus-phase intervention is accompanied by increased attention to visual tokens during decoding. Based on these observations, we instantiate a simple training-free inference-time intervention that replaces focus-phase low-attention values with an image-level mean value vector using statistics from a single forward pass. Experiments across multiple LVLM backbones demonstrate that this analysis-derived intervention reduces object hallucination with negligible additional runtime and remains compatible with existing inference-time mitigation methods.
Mitigating Hallucination in Large Language Models: A Capability-Oriented Survey on RAG, Reasoning, and Agentic Systems
Electronic Information School, Wuhan University（武汉大学电子信息学院）；School of Computing, Dublin City University（都柏林城市大学计算机学院）；School of Public Health, Wuhan University（武汉大学公共卫生学院）；Insight Centre for Data Analytics, University of Galway（Galway大学数据分析研究中心）；Insight Centre for Data Analytics, Dublin City University（都柏林城市大学数据分析研究中心）
In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation
City University of Hong Kong（香港城市大学）；National University of Singapore（新加坡国立大学）；Shanghai Jiao Tong University（上海交通大学）；Stanford University（斯坦福大学）；Penn State University（宾夕法尼亚州立大学）；Hong Kong University of Science and Technology（香港科技大学）
Looking Back and Forth: Cross-Image Attention Calibration and Attentive Preference Learning for Multi-Image Hallucination Mitigation
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Harbin Institute of Technology（哈尔滨工业大学）；Beijing Institute of Technology（北京理工大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学深圳分校）
Cross-Modal Attention Calibration for LVLM Hallucination Mitigation
Sun Yat-sen University（中山大学）；The University of Hong Kong（香港大学）；Meituan（美团）；Inspur Database Technology（Inspur数据库技术）；Guilin University of Electronic Technology（桂林电子科技大学）；Shenzhen Loop Area Institute（深圳河套学院）；Guangdong Key Laboratory of Big Data Analysis and Processing（广东大数据分析与处理重点实验室）
An Evolutionary Large Language Model for Hallucination Mitigation
BIOSTIM Laboratory Faculty of Medicine Salah Boubnider University Constantine, Algeria（BIOSTIM实验室医学院萨拉赫·布宾德大学阿尔及利亚科纳克特）；Department of IFA Faculty of NTIC Abdelhamid Mehri University Constantine, Algeria（IFA部门NTIC学院阿卜杜勒哈米德·梅赫里大学阿尔及利亚科纳克特）
RSHallu: Dual-Mode Hallucination Evaluation for Remote-Sensing Multimodal Large Language Models with Domain-Tailored Mitigation
College of Computer Science, Chongqing University（重庆大学计算机科学学院）；Heavy Rainfall Research Center of China（中国强降水研究中心）；CMA Key Open Laboratory of Transforming Climate Resources to Economy, Chongqing Institute of Meteorological Sciences（中国气象局气候资源转化经济重点开放实验室、重庆气象科学研究院）；Chongqing Metropolitan College of Science（重庆科学理工学院）；School of Intelligence Science（智能科学学院）；College of Artificial Intelligence, Harbin Institute of Technology（人工智能学院、哈尔滨工业大学）；BNU-UIC Institute of Artificial Intelligence（北京师范大学-国际学院人工智能与未来网络研究院）；Future Networks, Beijing Normal University at Zhuhai（未来网络、北京师范大学珠海分校）
Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation
School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University)（东南大学新一代人工智能技术及其交叉应用关键实验室）；Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所基础模型研究中心）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；Wuhan University of Technology（武汉理工大学）；National University of Singapore（新加坡国立大学）
HaloProbe: Bayesian Detection and Mitigation of Object Hallucinations in Vision-Language Models
Multimodal AI Lab, Technical University of Darmstadt（达姆施塔特工业大学多模态人工智能实验室）；Department of Computer Engineering, Sharif University of Technology（谢里夫理工大学计算机工程系）
Towards Interpretable Hallucination Analysis and Mitigation in LVLMs via Contrastive Neuron Steering
School of Electronic Engineering, Xidian University, Xi'an, China（西安电子科技大学电子工程学院）；School of Computer Science and Technology, Xidian University, Xi'an, China（西安电子科技大学计算机科学与技术学院）；College of Computer and Information, Hohai University, Nanjing, China（河海大学计算机与信息学院）；Institute for Infocomm Research, A*STAR, Singapore（新加坡资讯研究院）
Beyond Global Editing: Per-Instance Disentangled Subspaces for Training-Free Hallucination Mitigation in LVLMs
Macquarie University（麦考瑞大学）；York University（约克大学）；Northern Illinois University（北伊利诺伊大学）；University of Technology Sydney（悉尼科技大学）；North South University（北南大学）；Lancaster University（兰卡斯特大学）；Australian National University（澳大利亚国立大学）
