Buchumschlag

Mitigating Hallucinations in Large Vision-Language Models with Internal Fact-based Contrastive Decoding

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Wang, Chao, Zhou, Xuancheng, Fu, Weiwei, Zhou, Yang
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Computer Vision and Pattern Recognition Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding
von: Wang, Xintong, et al.
Veröffentlicht: (2024)

Delve into Visual Contrastive Decoding for Hallucination Mitigation of Large Vision-Language Models
von: Lee, Yi-Lun, et al.
Veröffentlicht: (2024)

Watch Closely: Mitigating Object Hallucinations in Large Vision-Language Models with Disentangled Decoding
von: Ma, Ruiqi, et al.
Veröffentlicht: (2025)

Mitigating Hallucinations in Large Vision-Language Models (LVLMs) via Language-Contrastive Decoding (LCD)
von: Manevich, Avshalom, et al.
Veröffentlicht: (2024)

Efficient Contrastive Decoding with Probabilistic Hallucination Detection - Mitigating Hallucinations in Large Vision Language Models -
von: Fieback, Laura, et al.
Veröffentlicht: (2025)

Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models
von: Zhang, Ce, et al.
Veröffentlicht: (2025)

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

Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding
von: Min, Kyungmin, et al.
Veröffentlicht: (2024)

Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language Models
von: Li, Bin, et al.
Veröffentlicht: (2025)

TPC: Cross-Temporal Prediction Connection for Vision-Language Model Hallucination Reduction
von: Wang, Chao, et al.
Veröffentlicht: (2025)

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

Mask What Matters: Mitigating Object Hallucinations in Multimodal Large Language Models with Object-Aligned Visual Contrastive Decoding
von: Chen, Boqi, et al.
Veröffentlicht: (2026)

Diving into Mitigating Hallucinations from a Vision Perspective for Large Vision-Language Models
von: Wang, Weihang, et al.
Veröffentlicht: (2025)

Mixture of Decoding: An Attention-Inspired Adaptive Decoding Strategy to Mitigate Hallucinations in Large Vision-Language Models
von: Chen, Xinlong, et al.
Veröffentlicht: (2025)

Black-Box Visual Prompt Engineering for Mitigating Object Hallucination in Large Vision Language Models
von: Woo, Sangmin, et al.
Veröffentlicht: (2025)

A Unified Hallucination Mitigation Framework for Large Vision-Language Models
von: Chang, Yue, et al.
Veröffentlicht: (2024)

SEASON: Mitigating Temporal Hallucination in Video Large Language Models via Self-Diagnostic Contrastive Decoding
von: Wu, Chang-Hsun, et al.
Veröffentlicht: (2025)

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

Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual Embeddings
von: Agrawal, Aakriti, et al.
Veröffentlicht: (2025)

VEGAS: Mitigating Hallucinations in Large Vision-Language Models via Vision-Encoder Attention Guided Adaptive Steering
von: Wang, Zihu, et al.
Veröffentlicht: (2025)

PAINT: Paying Attention to INformed Tokens to Mitigate Hallucination in Large Vision-Language Model
von: Arif, Kazi Hasan Ibn, et al.
Veröffentlicht: (2025)

ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models
von: Wan, Zifu, et al.
Veröffentlicht: (2025)

MINT: Mitigating Hallucinations in Large Vision-Language Models via Token Reduction
von: Wang, Chao, et al.
Veröffentlicht: (2025)

Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration
von: Fazli, Mehrdad, et al.
Veröffentlicht: (2025)

SDCD: Structure-Disrupted Contrastive Decoding for Mitigating Hallucinations in Large Vision-Language Models
von: Xia, Yuxuan, et al.
Veröffentlicht: (2026)

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

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

VaLiD: Mitigating the Hallucination of Large Vision Language Models by Visual Layer Fusion Contrastive Decoding
von: Wang, Jiaqi, et al.
Veröffentlicht: (2024)

ESREAL: Exploiting Semantic Reconstruction to Mitigate Hallucinations in Vision-Language Models
von: Kim, Minchan, et al.
Veröffentlicht: (2024)

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

Med-VCD: Mitigating Hallucination for Medical Large Vision Language Models through Visual Contrastive Decoding
von: Mahdavi, Zahra, et al.
Veröffentlicht: (2025)

MaskCD: Mitigating LVLM Hallucinations by Image Head Masked Contrastive Decoding
von: Deng, Jingyuan, et al.
Veröffentlicht: (2025)

HELPD: Mitigating Hallucination of LVLMs by Hierarchical Feedback Learning with Vision-enhanced Penalty Decoding
von: Yuan, Fan, et al.
Veröffentlicht: (2024)

The Mirage of Performance Gains: Why Contrastive Decoding Fails to Mitigate Object Hallucinations in MLLMs?
von: Yin, Hao, et al.
Veröffentlicht: (2025)

Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs
von: Fang, Hao, et al.
Veröffentlicht: (2025)

Extracting Visual Facts from Intermediate Layers for Mitigating Hallucinations in Multimodal Large Language Models
von: Zhou, Haoran, et al.
Veröffentlicht: (2025)

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

SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding
von: Park, Woohyeon, et al.
Veröffentlicht: (2025)

Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding
von: Deng, Ailin, et al.
Veröffentlicht: (2024)

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