Imagen de Portada

Causal Tracing of Object Representations in Large Vision Language Models: Mechanistic Interpretability and Hallucination Mitigation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Qiming, Ye, Zekai, Feng, Xiaocheng, Zhong, Weihong, Ma, Weitao, Feng, Xiachong
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

CAI: Caption-Sensitive Attention Intervention for Mitigating Object Hallucination in Large Vision-Language Models
por: Li, Qiming, et al.
Publicado: (2025)

Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models
por: Zhong, Weihong, et al.
Publicado: (2024)

CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering
por: Li, Qiming, et al.
Publicado: (2026)

Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering
por: Li, Qiming, et al.
Publicado: (2025)

CLAIM: Mitigating Multilingual Object Hallucination in Large Vision-Language Models with Cross-Lingual Attention Intervention
por: Ye, Zekai, et al.
Publicado: (2025)

Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations
por: Jiang, Nick, et al.
Publicado: (2024)

Mitigating Hallucination in Large Vision-Language Models through Aligning Attention Distribution to Information Flow
por: Zhao, Jianfei, et al.
Publicado: (2025)

Reflective Instruction Tuning: Mitigating Hallucinations in Large Vision-Language Models
por: Zhang, Jinrui, et al.
Publicado: (2024)

Mitigating Hallucinations in Large Vision-Language Models via Causal Route Gating
por: Cheng, Zhe, et al.
Publicado: (2026)

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens
por: Jiang, Zhangqi, et al.
Publicado: (2024)

VORD: Visual Ordinal Calibration for Mitigating Object Hallucinations in Large Vision-Language Models
por: Neo, Dexter, et al.
Publicado: (2024)

Watch Closely: Mitigating Object Hallucinations in Large Vision-Language Models with Disentangled Decoding
por: Ma, Ruiqi, 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)

Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
por: Zhou, Yiyang, et al.
Publicado: (2023)

Mitigating Object Hallucinations in Large Vision-Language Models via Attention Calibration
por: Zhu, Younan, et al.
Publicado: (2025)

Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection
por: Yang, Le, et al.
Publicado: (2024)

Exploring Causes and Mitigation of Hallucinations in Large Vision Language Models
por: Sun, Yaqi, et al.
Publicado: (2025)

Segmentation-Based Attention Entropy: Detecting and Mitigating Object Hallucinations in Large Vision-Language Models
por: Song, Jiale, et al.
Publicado: (2026)

Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering
por: Liu, Shuliang, et al.
Publicado: (2026)

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention
por: Zhao, Jianfei, et al.
Publicado: (2025)

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

Seeing It or Not? Interpretable Vision-aware Latent Steering to Mitigate Object Hallucinations
por: Chen, Boxu, et al.
Publicado: (2025)

Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation
por: Zhu, Xingyu, et al.
Publicado: (2026)

Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) Models
por: Liu, Yufang, et al.
Publicado: (2024)

Causally-Grounded Dual-Path Attention Intervention for Object Hallucination Mitigation in LVLMs
por: Yu, Liu, 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)

Dual-Pathway Circuits of Object Hallucination in Vision-Language Models
por: Liu, Jiaxin, et al.
Publicado: (2026)

Object Hallucination-Free Reinforcement Unlearning for Vision-Language Models
por: Jia, Kaidi, et al.
Publicado: (2026)

HalluCXR: Benchmarking and Mitigating Hallucinations in Medical Vision-Language Models for Chest Radiograph Interpretation
por: Wang, Haoyu, et al.
Publicado: (2026)

What Makes "Good" Distractors for Object Hallucination Evaluation in Large Vision-Language Models?
por: Xie, Ming-Kun, et al.
Publicado: (2025)

OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Model
por: Chen, Qiguang, et al.
Publicado: (2026)

Retrieval Visual Contrastive Decoding to Mitigate Object Hallucinations in Large Vision-Language Models
por: Lee, Jihoon, et al.
Publicado: (2025)

HaloProbe: Bayesian Detection and Mitigation of Object Hallucinations in Vision-Language Models
por: Zohrabi, Reihaneh, et al.
Publicado: (2026)

Mitigating Multilingual Hallucination in Large Vision-Language Models
por: Qu, Xiaoye, et al.
Publicado: (2024)

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

MedHEval: Benchmarking Hallucinations and Mitigation Strategies in Medical Large Vision-Language Models
por: Chang, Aofei, et al.
Publicado: (2025)

HTDC: Hesitation-Triggered Differential Calibration for Mitigating Hallucination in Large Vision-Language Models
por: Liu, Xinyun
Publicado: (2026)

Mitigating Dialogue Hallucination for Large Vision Language Models via Adversarial Instruction Tuning
por: Park, Dongmin, et al.
Publicado: (2024)

Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models
por: Li, Lei, et al.
Publicado: (2024)

Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models
por: Zhang, Chengsheng, et al.
Publicado: (2026)