Imagen de Portada

Tracing and Mitigating Hallucinations in Multimodal LLMs via Dynamic Attention Localization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yang, Tiancheng, Zhang, Lin, Lin, Jiaye, Hu, Guimin, Wang, Di, Hu, Lijie
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Mitigating Behavioral Hallucination in Multimodal Large Language Models for Sequential Images
por: You, Liangliang, et al.
Publicado: (2025)

Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality
por: Zhou, Guanyu, et al.
Publicado: (2024)

Visual Attention Drifts,but Anchors Hold:Mitigating Hallucination in Multimodal Large Language Models via Cross-Layer Visual Anchors
por: Yang, Chengxu, et al.
Publicado: (2026)

Seeing Clearly without Training: Mitigating Hallucinations in Multimodal LLMs for Remote Sensing
por: Liu, Yi, et al.
Publicado: (2026)

Text-Guided Layer Fusion Mitigates Hallucination in Multimodal LLMs
por: Lin, Chenchen, et al.
Publicado: (2026)

Mitigating Hallucination in Multimodal LLMs with Layer Contrastive Decoding
por: Tong, Bingkui, et al.
Publicado: (2025)

SmartSight: Mitigating Hallucination in Video-LLMs Without Compromising Video Understanding via Temporal Attention Collapse
por: Sun, Yiming, et al.
Publicado: (2025)

Backdooring CLIP through Concept Confusion
por: Hu, Lijie, et al.
Publicado: (2025)

Cross-Modal Attention Calibration for LVLM Hallucination Mitigation
por: Li, Jiaming, et al.
Publicado: (2025)

Mitigating Multimodal Hallucination via Phase-wise Self-reward
por: Zhang, Yu, et al.
Publicado: (2026)

Intervene-All-Paths: Unified Mitigation of LVLM Hallucinations across Alignment Formats
por: Qian, Jiaye, et al.
Publicado: (2025)

Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention
por: An, Wenbin, et al.
Publicado: (2024)

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding
por: Tang, Feilong, et al.
Publicado: (2025)

ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models
por: Chen, Junzhe, et al.
Publicado: (2024)

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation
por: Tang, Lexiang, et al.
Publicado: (2025)

Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought Models
por: Ma, Ji, et al.
Publicado: (2026)

Mitigating Object Hallucinations in LVLMs via Attention Imbalance Rectification
por: Sun, Han, et al.
Publicado: (2026)

Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation
por: Jia, Sihang, et al.
Publicado: (2026)

Benchmarking and Mitigating Sycophancy in Medical Vision Language Models
por: Xu, Juangui, et al.
Publicado: (2025)

Mitigating Object Hallucination via Concentric Causal Attention
por: Xing, Yun, et al.
Publicado: (2024)

Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering
por: Cai, Jianfeng, et al.
Publicado: (2025)

Mitigating Hallucination in Visual-Language Models via Re-Balancing Contrastive Decoding
por: Liang, Xiaoyu, et al.
Publicado: (2024)

Mitigating Object Hallucination via Robust Local Perception Search
por: Gao, Zixian, et al.
Publicado: (2025)

Scalpel: Fine-Grained Alignment of Attention Activation Manifolds via Mixture Gaussian Bridges to Mitigate Multimodal Hallucination
por: Shi, Ziqiang, et al.
Publicado: (2026)

Mitigating Multimodal Hallucinations via Gradient-based Self-Reflection
por: Wang, Shan, et al.
Publicado: (2025)

Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images
por: Yang, Qishun, et al.
Publicado: (2026)

Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization
por: Compagnoni, Alberto, et al.
Publicado: (2025)

Modality Bias in LVLMs: Analyzing and Mitigating Object Hallucination via Attention Lens
por: Zheng, Haohan, et al.
Publicado: (2025)

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification
por: Zhang, Jiacheng, et al.
Publicado: (2026)

Beyond Single Models: Mitigating Multimodal Hallucinations via Adaptive Token Ensemble Decoding
por: Li, Jinlin, et al.
Publicado: (2025)

Revealing and Enhancing Core Visual Regions: Harnessing Internal Attention Dynamics for Hallucination Mitigation in LVLMs
por: Lyu, Guangtao, et al.
Publicado: (2026)

MM-Snowball: Evaluating and Mitigating Hallucination Snowballing in Multimodal Multi-Turn Dialogue
por: Jiang, Yue, et al.
Publicado: (2026)

Learning from Fine-Grained Visual Discrepancies: Mitigating Multimodal Hallucinations via In-Context Visual Contrastive Optimization
por: Deng, Haolin, et al.
Publicado: (2026)

Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment
por: Chang, Kai-Po, et al.
Publicado: (2025)

When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding
por: Shu, Yan, et al.
Publicado: (2025)

V-ITI: Mitigating Hallucinations in Multimodal Large Language Models via Visual Inference-Time Intervention
por: Sun, Nan, et al.
Publicado: (2025)

Attention Hijackers: Detect and Disentangle Attention Hijacking in LVLMs for Hallucination Mitigation
por: Chen, Beitao, et al.
Publicado: (2025)

Interpreting and Mitigating Hallucination in MLLMs through Multi-agent Debate
por: Lin, Zheng, et al.
Publicado: (2024)

Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models
por: He, Zhentao, et al.
Publicado: (2025)

Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinations
por: Lu, Yifan, et al.
Publicado: (2025)