Copertina

Two Causes, Not One: Rethinking Omission and Fabrication Hallucinations in MLLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Si, Guangzong, Yin, Hao, Li, Xianfei, Ding, Qing, Liao, Wenlong, He, Tao, Peng, Pai
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

Generative Planning with 3D-vision Language Pre-training for End-to-End Autonomous Driving
di: Li, Tengpeng, et al.
Pubblicazione: (2025)

Open-Vocabulary Object Detection via Neighboring Region Attention Alignment
di: Qiang, Sunyuan, et al.
Pubblicazione: (2024)

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

Rethinking Temporal Fusion with a Unified Gradient Descent View for 3D Semantic Occupancy Prediction
di: Chen, Dubing, et al.
Pubblicazione: (2025)

You Only Click Once: Single Point Weakly Supervised 3D Instance Segmentation for Autonomous Driving
di: Jiang, Guangfeng, et al.
Pubblicazione: (2025)

The DAWN of World-Action Interactive Models
di: Lu, Hongbo, et al.
Pubblicazione: (2026)

Semantic Causality-Aware Vision-Based 3D Occupancy Prediction
di: Chen, Dubing, et al.
Pubblicazione: (2025)

ARGUS: Hallucination and Omission Evaluation in Video-LLMs
di: Rawal, Ruchit, et al.
Pubblicazione: (2025)

VisionNVS: Self-Supervised Inpainting for Novel View Synthesis under the Virtual-Shift Paradigm
di: Lu, Hongbo, et al.
Pubblicazione: (2026)

One Token, Two Fates: A Unified Framework via Vision Token Manipulation Against MLLMs Hallucination
di: Fa, Zhan, et al.
Pubblicazione: (2026)

Attention Reallocation: Towards Zero-cost and Controllable Hallucination Mitigation of MLLMs
di: Tu, Chongjun, et al.
Pubblicazione: (2025)

FREAK: A Fine-grained Hallucination Evaluation Benchmark for Advanced MLLMs
di: Yin, Zhihan, et al.
Pubblicazione: (2026)

TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs
di: Zhang, Kejia, et al.
Pubblicazione: (2025)

RedundancyLens: Revealing and Exploiting Visual Token Processing Redundancy for Efficient Decoder-Only MLLMs
di: Li, Hongliang, et al.
Pubblicazione: (2025)

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

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

A Real-Time On-Device Defect Detection Framework for Laser Power-Meter Sensors via Unsupervised Learning
di: Zheng, Dongqi, et al.
Pubblicazione: (2025)

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

Explore the Hallucination on Low-level Perception for MLLMs
di: Sun, Yinan, et al.
Pubblicazione: (2024)

Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation
di: Huang, Zhe, et al.
Pubblicazione: (2025)

Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs
di: Wang, Zitian, et al.
Pubblicazione: (2025)

On Discriminative vs. Generative classifiers: Rethinking MLLMs for Action Understanding
di: Pang, Zhanzhong, et al.
Pubblicazione: (2026)

One Model, Two Minds: Task-Conditioned Reasoning for Unified Image Quality and Aesthetic Assessment
di: Yin, Wen, et al.
Pubblicazione: (2026)

Clinical Cognition Alignment for Gastrointestinal Diagnosis with Multimodal LLMs
di: Zheng, Huan, et al.
Pubblicazione: (2026)

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

Diagnosing and Correcting Concept Omission in Multimodal Diffusion Transformers
di: Baek, Kanghyun, et al.
Pubblicazione: (2026)

Detecting Omissions in Geographic Maps through Computer Vision
di: Nguyen, Phuc D. A., et al.
Pubblicazione: (2024)

Ground What You See: Hallucination-Resistant MLLMs via Caption Feedback, Diversity-Aware Sampling, and Conflict Regularization
di: Pan, Miao, et al.
Pubblicazione: (2026)

Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment
di: Sarkar, Pritam, et al.
Pubblicazione: (2024)

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

ReEXplore: Improving MLLMs for Embodied Exploration with Contextualized Retrospective Experience Replay
di: Zhang, Gengyuan, et al.
Pubblicazione: (2025)

Deep Learning for Inertial Positioning: A Survey
di: Chen, Changhao, et al.
Pubblicazione: (2023)

NOAH: Benchmarking Narrative Prior driven Hallucination and Omission in Video Large Language Models
di: Lee, Kyuho, et al.
Pubblicazione: (2025)

FINER: MLLMs Hallucinate under Fine-grained Negative Queries
di: Xiao, Rui, et al.
Pubblicazione: (2026)

Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning
di: Zhang, Bob, et al.
Pubblicazione: (2025)

Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReID
di: Tan, Wentao, et al.
Pubblicazione: (2024)

When Looking Is Not Enough: Visual Attention Structure Reveals Hallucination in MLLMs
di: Cao, Fanpu, et al.
Pubblicazione: (2026)

AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation
di: Wang, Junyang, et al.
Pubblicazione: (2023)