Imagen de Portada

Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Xiaoyuan, Wang, Wenxuan, Yuan, Youliang, Huang, Jen-tse, Liu, Qiuzhi, He, Pinjia, Tu, Zhaopeng
Formato:	Preprint
Publicado:	2024
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

Can't See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs
por: Wang, Wenxuan, et al.
Publicado: (2025)

GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
por: Yuan, Youliang, et al.
Publicado: (2023)

Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step
por: Wang, Wenxuan, et al.
Publicado: (2024)

Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs
por: Huang, Jen-Tse, et al.
Publicado: (2025)

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
por: Yuan, Youliang, et al.
Publicado: (2024)

VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models
por: Huang, Jen-tse, et al.
Publicado: (2025)

Towards Evaluating Proactive Risk Awareness of Multimodal Language Models
por: Yuan, Youliang, et al.
Publicado: (2025)

AI Sees Your Location, But With A Bias Toward The Wealthy World
por: Huang, Jingyuan, et al.
Publicado: (2025)

Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards
por: Yuan, Youliang, et al.
Publicado: (2025)

All Languages Matter: On the Multilingual Safety of Large Language Models
por: Wang, Wenxuan, et al.
Publicado: (2023)

Who is ChatGPT? Benchmarking LLMs' Psychological Portrayal Using PsychoBench
por: Huang, Jen-tse, et al.
Publicado: (2023)

Difficult Task Yes but Simple Task No: Unveiling the Laziness in Multimodal LLMs
por: Zhao, Sihang, et al.
Publicado: (2024)

LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models
por: Wan, Yuxuan, et al.
Publicado: (2024)

How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments
por: Huang, Jen-tse, et al.
Publicado: (2024)

On the Shortcut Learning in Multilingual Neural Machine Translation
por: Wang, Wenxuan, et al.
Publicado: (2024)

New Job, New Gender? Measuring the Social Bias in Image Generation Models
por: Wang, Wenxuan, et al.
Publicado: (2024)

Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models
por: Zhu, Tinghui, et al.
Publicado: (2024)

SHAPE: Unifying Safety, Helpfulness and Pedagogy for Educational LLMs
por: Zhao, Sihang, et al.
Publicado: (2026)

Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards
por: Liu, Xiaoyuan, et al.
Publicado: (2025)

Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench
por: Huang, Jen-tse, et al.
Publicado: (2023)

Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models
por: Wang, Wenxuan, et al.
Publicado: (2023)

PaSBench-Video: A Streaming Video Benchmark for Proactive Safety Warning
por: Zhao, Yusong, et al.
Publicado: (2026)

Identifying the Achilles' Heel: An Iterative Method for Dynamically Uncovering Factual Errors in Large Language Models
por: Wang, Wenxuan, et al.
Publicado: (2024)

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
por: Wang, Yue, et al.
Publicado: (2025)

Vision Enhancing LLMs: Empowering Multimodal Knowledge Storage and Sharing in LLMs
por: Li, Yunxin, et al.
Publicado: (2023)

Probing Multimodal Large Language Models on Cognitive Biases in Chinese Short-Video Misinformation
por: Huang, Jen-tse, et al.
Publicado: (2026)

On the Failure of Latent State Persistence in Large Language Models
por: Huang, Jen-tse, et al.
Publicado: (2025)

From Sight to Insight: Improving Visual Reasoning Capabilities of Multimodal Models via Reinforcement Learning
por: Sharif, Omar, et al.
Publicado: (2026)

The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems
por: Ma, Xinbei, et al.
Publicado: (2025)

How Well Can LLMs Echo Us? Evaluating AI Chatbots' Role-Play Ability with ECHO
por: Ng, Man Tik, et al.
Publicado: (2024)

The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
por: Ji, Ke, et al.
Publicado: (2025)

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
por: Wang, Mengru, et al.
Publicado: (2025)

FairCoder: Evaluating Social Bias of LLMs in Code Generation
por: Du, Yongkang, et al.
Publicado: (2025)

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention
por: Liu, Wenjie, et al.
Publicado: (2026)

UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
por: Jiang, Houcheng, et al.
Publicado: (2026)

ComboBench: Can LLMs Manipulate Physical Devices to Play Virtual Reality Games?
por: Li, Shuqing, et al.
Publicado: (2025)

Can LLMs Grasp Implicit Cultural Values? Benchmarking LLMs' Cultural Intelligence with CQ-Bench
por: Liu, Ziyi, et al.
Publicado: (2025)

Conflict Adaptation in Vision-Language Models
por: Hu, Xiaoyang
Publicado: (2025)

A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?
por: Chen, Ada, et al.
Publicado: (2025)

DeepSight: Bridging Depth Maps and Language with a Depth-Driven Multimodal Model
por: Yang, Hao, et al.
Publicado: (2026)