Cover Image

Causal Probing for Internal Visual Representations in Multimodal Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Deng, Zehao, Ju, Tianjie, Wu, Zheng, He, Liangbo, Lan, Jun, Zhu, Huijia, Wang, Weiqiang, Zhang, Zhuosheng
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Training High-Level Schedulers with Execution-Feedback Reinforcement Learning for Long-Horizon GUI Automation
by: Deng, Zehao, et al.
Published: (2025)

Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
by: Wei, Lai, et al.
Published: (2026)

HoneyTrap: Deceiving Large Language Model Attackers to Honeypot Traps with Resilient Multi-Agent Defense
by: Li, Siyuan, et al.
Published: (2026)

Disagreements in Reasoning: How a Model's Thinking Process Dictates Persuasion in Multi-Agent Systems
by: Zhao, Haodong, et al.
Published: (2025)

Smoothing Grounding and Reasoning for MLLM-Powered GUI Agents with Query-Oriented Pivot Tasks
by: Wu, Zongru, et al.
Published: (2025)

InsightVision: A Comprehensive, Multi-Level Chinese-based Benchmark for Evaluating Implicit Visual Semantics in Large Vision Language Models
by: Yin, Xiaofei, et al.
Published: (2025)

Dynamic Generation of Personalities with Large Language Models
by: Liu, Jianzhi, et al.
Published: (2024)

See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles
by: Wu, Zongru, et al.
Published: (2025)

Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models
by: Liu, Yanjiang, et al.
Published: (2025)

Probing Multimodal Large Language Models for Global and Local Semantic Representations
by: Tao, Mingxu, et al.
Published: (2024)

NSmark: Null Space Based Black-box Watermarking Defense Framework for Language Models
by: Zhao, Haodong, et al.
Published: (2024)

Probing Causality Manipulation of Large Language Models
by: Zhang, Chenyang, et al.
Published: (2024)

Causality for Large Language Models
by: Wu, Anpeng, et al.
Published: (2024)

When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Models
by: Liu, Ziyu, et al.
Published: (2026)

Revealing Multimodal Causality with Large Language Models
by: Li, Jin, et al.
Published: (2025)

CausalVLBench: Benchmarking Visual Causal Reasoning in Large Vision-Language Models
by: Komanduri, Aneesh, et al.
Published: (2025)

Causal-LLaVA: Causal Disentanglement for Mitigating Hallucination in Multimodal Large Language Models
by: Hu, Xinmiao, et al.
Published: (2025)

Unleashing the Intrinsic Visual Representation Capability of Multimodal Large Language Models
by: Li, Hengzhuang, et al.
Published: (2025)

ReProbe: Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models
by: Ni, Jingwei, et al.
Published: (2025)

Select-Then-Decompose: From Empirical Analysis to Adaptive Selection Strategy for Task Decomposition in Large Language Models
by: Liu, Shuodi, et al.
Published: (2025)

Interpretable and Reliable Detection of AI-Generated Images via Grounded Reasoning in MLLMs
by: Ji, Yikun, et al.
Published: (2025)

Exploring the Transferability of Visual Prompting for Multimodal Large Language Models
by: Zhang, Yichi, et al.
Published: (2024)

Taxonomy-Aware Representation Alignment for Hierarchical Visual Recognition with Large Multimodal Models
by: He, Hulingxiao, et al.
Published: (2026)

Generalizable Chain-of-Thought Prompting in Mixed-task Scenarios with Large Language Models
by: Zou, Anni, et al.
Published: (2023)

Self-Prompting Large Language Models for Zero-Shot Open-Domain QA
by: Li, Junlong, et al.
Published: (2022)

OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models
by: Zheng, Hao, et al.
Published: (2025)

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images
by: Ji, Yikun, et al.
Published: (2025)

ChemVTS-Bench: Evaluating Visual-Textual-Symbolic Reasoning of Multimodal Large Language Models in Chemistry
by: Huang, Zhiyuan, et al.
Published: (2025)

NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models
by: Zhang, Chuhan, et al.
Published: (2025)

Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoning
by: Tan, Hao, et al.
Published: (2025)

Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining
by: Wu, Zongru, et al.
Published: (2024)

Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language Models
by: Li, Kunhao, et al.
Published: (2025)

Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning
by: Chen, Junkai, et al.
Published: (2026)

VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models
by: Zhu, Zihao, et al.
Published: (2023)

Efficient Detection of Toxic Prompts in Large Language Models
by: Liu, Yi, et al.
Published: (2024)

A Survey of Hallucination in Large Visual Language Models
by: Lan, Wei, et al.
Published: (2024)

Internalized Self-Correction for Large Language Models
by: Upadhyaya, Nishanth, et al.
Published: (2024)

Exploring Multimodal Prompt for Visualization Authoring with Large Language Models
by: Wen, Zhen, et al.
Published: (2025)

Benchmarking the Thinking Mode of Multimodal Large Language Models in Clinical Tasks
by: Hong, Jindong, et al.
Published: (2025)

MEGen: Generative Backdoor into Large Language Models via Model Editing
by: Qiu, Jiyang, et al.
Published: (2024)