Buchumschlag

Focus Matters: Phase-Aware Suppression for Hallucination in Vision-Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Kim, Sohyeon, Yoon, Sang Yeon, Kong, Kyeongbo
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

NoLan: Mitigating Object Hallucinations in Large Vision-Language Models via Dynamic Suppression of Language Priors
von: Ren, Lingfeng, et al.
Veröffentlicht: (2026)

What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal Models
von: Kim, Junho, et al.
Veröffentlicht: (2024)

AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models
von: Baek, Changwoo, et al.
Veröffentlicht: (2026)

Multi-Object Hallucination in Vision-Language Models
von: Chen, Xuweiyi, et al.
Veröffentlicht: (2024)

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

Benchmarking Deflection and Hallucination in Large Vision-Language Models
von: Moratelli, Nicholas, et al.
Veröffentlicht: (2026)

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

VLind-Bench: Measuring Language Priors in Large Vision-Language Models
von: Lee, Kang-il, et al.
Veröffentlicht: (2024)

Alleviating Hallucination in Large Vision-Language Models with Active Retrieval Augmentation
von: Qu, Xiaoye, et al.
Veröffentlicht: (2024)

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

TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention
von: Duan, Jinhao, et al.
Veröffentlicht: (2025)

On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models
von: Seo, Hoigi, et al.
Veröffentlicht: (2025)

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

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

Programmable-Room: Interactive Textured 3D Room Meshes Generation Empowered by Large Language Models
von: Kim, Jihyun, 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)

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

Mitigating Hallucinations in Large Vision-Language Models via Entity-Centric Multimodal Preference Optimization
von: Wu, Jiulong, et al.
Veröffentlicht: (2025)

MedHallTune: An Instruction-Tuning Benchmark for Mitigating Medical Hallucination in Vision-Language Models
von: Yan, Qiao, et al.
Veröffentlicht: (2025)

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

CDH-Bench: A Commonsense-Driven Hallucination Benchmark for Evaluating Visual Fidelity in Vision-Language Models
von: Chen, Kesheng, et al.
Veröffentlicht: (2026)

First Logit Boosting: Visual Grounding Method to Mitigate Object Hallucination in Large Vision-Language Models
von: Ha, Jiwoo, et al.
Veröffentlicht: (2026)

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

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

Tone Matters: The Impact of Linguistic Tone on Hallucination in VLMs
von: Hong, Weihao, et al.
Veröffentlicht: (2026)

Situational Awareness Matters in 3D Vision Language Reasoning
von: Man, Yunze, et al.
Veröffentlicht: (2024)

ChartHal: A Fine-grained Framework Evaluating Hallucination of Large Vision Language Models in Chart Understanding
von: Wang, Xingqi, et al.
Veröffentlicht: (2025)

Cross-Cultural Value Awareness in Large Vision-Language Models
von: Howard, Phillip, et al.
Veröffentlicht: (2026)

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

Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains
von: Zhang, Juntian, et al.
Veröffentlicht: (2025)

Hyperbolic Safety-Aware Vision-Language Models
von: Poppi, Tobia, et al.
Veröffentlicht: (2025)

Unified Triplet-Level Hallucination Evaluation for Large Vision-Language Models
von: Wu, Junjie, et al.
Veröffentlicht: (2024)

AttentionHand: Text-driven Controllable Hand Image Generation for 3D Hand Reconstruction in the Wild
von: Park, Junho, et al.
Veröffentlicht: (2024)

Learning What Matters: Dynamic Dimension Selection and Aggregation for Interpretable Vision-Language Reward Modeling
von: Chen, Qiyuan, et al.
Veröffentlicht: (2026)

Bayesian Principles Improve Prompt Learning In Vision-Language Models
von: Kim, Mingyu, et al.
Veröffentlicht: (2025)

Toward More Reliable Artificial Intelligence: Reducing Hallucinations in Vision-Language Models
von: Sanogo, Kassoum, et al.
Veröffentlicht: (2025)

SegSub: Evaluating Robustness to Knowledge Conflicts and Hallucinations in Vision-Language Models
von: Carragher, Peter, et al.
Veröffentlicht: (2025)

Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models
von: Wu, Junfei, et al.
Veröffentlicht: (2024)

KOFFVQA: An Objectively Evaluated Free-form VQA Benchmark for Large Vision-Language Models in the Korean Language
von: Kim, Yoonshik, et al.
Veröffentlicht: (2025)

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