Copertina

The Mirage of Performance Gains: Why Contrastive Decoding Fails to Mitigate Object Hallucinations in MLLMs?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yin, Hao, Si, Guangzong, Wang, Zilei
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language Models
di: Yin, Hao, et al.
Pubblicazione: (2025)

Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference
di: Yin, Hao, et al.
Pubblicazione: (2025)

Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations
di: Li, Shuo, et al.
Pubblicazione: (2025)

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

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

CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding
di: Zhang, Xi, et al.
Pubblicazione: (2025)

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

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

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

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

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

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

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

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

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

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

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

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

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

Two Causes, Not One: Rethinking Omission and Fabrication Hallucinations in MLLMs
di: Si, Guangzong, et al.
Pubblicazione: (2025)

CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs
di: Kan, Zhehan, et al.
Pubblicazione: (2024)

MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
di: Wang, Chenxi, et al.
Pubblicazione: (2024)

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

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

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

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

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

Mitigating Hallucinations in Video Large Language Models via Spatiotemporal-Semantic Contrastive Decoding
di: Gao, Yuansheng, et al.
Pubblicazione: (2026)

ChartCap: Mitigating Hallucination of Dense Chart Captioning
di: Lim, Junyoung, et al.
Pubblicazione: (2025)

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

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

AdaCodec: A Predictive Visual Code for Video MLLMs
di: Hou, Haowen, et al.
Pubblicazione: (2026)

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

Why LVLMs Are More Prone to Hallucinations in Longer Responses: The Role of Context
di: Zheng, Ge, et al.
Pubblicazione: (2025)

Mitigating Visual Hallucinations via Semantic Curriculum Preference Optimization in MLLMs
di: Li, Yuanshuai, et al.
Pubblicazione: (2025)

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

Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance
di: Zhao, Linxi, et al.
Pubblicazione: (2024)

Mitigating Hallucinations in Multimodal Spatial Relations through Constraint-Aware Prompting
di: Wu, Jiarui, et al.
Pubblicazione: (2025)

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

Octopus: Alleviating Hallucination via Dynamic Contrastive Decoding
di: Suo, Wei, et al.
Pubblicazione: (2025)