Imagen de Portada

Grounded Visual Factualization: Factual Anchor-Based Finetuning for Enhancing MLLM Factual Consistency

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Morbiato, Filippo, Romano, Luca, Persona, Alessandro
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language 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

LLM-Bootstrapped Targeted Finding Guidance for Factual MLLM-based Medical Report Generation
por: Yang, Cunyuan, et al.
Publicado: (2026)

Can VLMs Recall Factual Associations From Visual References?
por: Ashok, Dhananjay, et al.
Publicado: (2025)

VC-Inspector: Advancing Reference-free Evaluation of Video Captions with Factual Analysis
por: Dipta, Shubhashis Roy, et al.
Publicado: (2025)

Towards Statistical Factuality Guarantee for Large Vision-Language Models
por: Li, Zhuohang, et al.
Publicado: (2025)

"See the World, Discover Knowledge": A Chinese Factuality Evaluation for Large Vision Language Models
por: Gu, Jihao, et al.
Publicado: (2025)

LLM-RG4: Flexible and Factual Radiology Report Generation across Diverse Input Contexts
por: Wang, Zhuhao, et al.
Publicado: (2024)

KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality
por: Ren, Baochang, et al.
Publicado: (2025)

T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts
por: Huang, Ziwei, et al.
Publicado: (2024)

FAGER: Factually Grounded Evaluation and Refinement of Text-to-Image Models
por: Lim, Youngsun, et al.
Publicado: (2026)

Factuality Matters: When Image Generation and Editing Meet Structured Visuals
por: Zhuo, Le, et al.
Publicado: (2025)

OraPO: Oracle-educated Reinforcement Learning for Data-efficient and Factual Radiology Report Generation
por: Chen, Zhuoxiao, et al.
Publicado: (2025)

The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented Intervention
por: Wan, Yixin, et al.
Publicado: (2024)

RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Models
por: Xia, Peng, et al.
Publicado: (2024)

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality
por: Newman, Benjamin, et al.
Publicado: (2025)

Revolutionizing Radiology Workflow with Factual and Efficient CXR Report Generation
por: Sukjai, Pimchanok, et al.
Publicado: (2025)

OVFact: Measuring and Improving Open-Vocabulary Factuality for Long Caption Models
por: Wysoczańska, Monika, et al.
Publicado: (2025)

Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models
por: Cao, Meng, et al.
Publicado: (2025)

Understanding Finetuning for Factual Knowledge Extraction
por: Ghosal, Gaurav, et al.
Publicado: (2024)

AFTER: Mitigating the Object Hallucination of LVLM via Adaptive Factual-Guided Activation Editing
por: Wang, Tianbo, et al.
Publicado: (2026)

FACE-net: Factual Calibration and Emotion Augmentation for Retrieval-enhanced Emotional Video Captioning
por: Chen, Weidong, et al.
Publicado: (2026)

MedFact-R1: Towards Factual Medical Reasoning via Pseudo-Label Augmentation
por: Li, Gengliang, et al.
Publicado: (2025)

Beyond Detection: Multi-Scale Hidden-Code for Natural Image Deepfake Recovery and Factual Retrieval
por: Chen, Yuan-Chih, et al.
Publicado: (2026)

Similarity over Factuality: Are we making progress on multimodal out-of-context misinformation detection?
por: Papadopoulos, Stefanos-Iordanis, et al.
Publicado: (2024)

INFACT: A Diagnostic Benchmark for Induced Faithfulness and Factuality Hallucinations in Video-LLMs
por: Yang, Junqi, et al.
Publicado: (2026)

Addressing Image Hallucination in Text-to-Image Generation through Factual Image Retrieval
por: Lim, Youngsun, et al.
Publicado: (2024)

Multi-Modal Hallucination Control by Visual Information Grounding
por: Favero, Alessandro, et al.
Publicado: (2024)

Open Multimodal Retrieval-Augmented Factual Image Generation
por: Tian, Yang, et al.
Publicado: (2025)

Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage
por: Lee, Saehyung, et al.
Publicado: (2024)

Visual Puns from Idioms: An Iterative LLM-T2IM-MLLM Framework
por: Xiao, Kelaiti, et al.
Publicado: (2025)

Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey
por: Kuang, Jiayi, et al.
Publicado: (2024)

Using Similarity to Evaluate Factual Consistency in Summaries
por: Ye, Yuxuan, et al.
Publicado: (2024)

Beyond Generation: Multi-Hop Reasoning for Factual Accuracy in Vision-Language Models
por: Hossain, Shamima
Publicado: (2025)

Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations
por: Yang, Ziyan, et al.
Publicado: (2022)

Watermarking for Factuality: Guiding Vision-Language Models Toward Truth via Tri-layer Contrastive Decoding
por: Back, Kyungryul, et al.
Publicado: (2025)

GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images
por: Lan, Xiang, et al.
Publicado: (2025)

HKD4VLM: A Progressive Hybrid Knowledge Distillation Framework for Robust Multimodal Hallucination and Factuality Detection in VLMs
por: Zhang, Zijian, et al.
Publicado: (2025)

AnchorOPT: Towards Optimizing Dynamic Anchors for Adaptive Prompt Learning
por: Li, Zheng, et al.
Publicado: (2025)

Learning to Reason for Factuality
por: Chen, Xilun, et al.
Publicado: (2025)

VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors
por: Shahgir, Haz Sameen, et al.
Publicado: (2026)

mFACE: Multilingual Summarization with Factual Consistency Evaluation
por: Aharoni, Roee, et al.
Publicado: (2022)