Cover Image

Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Qin, Shang, Chao, Liu, Ling, Pappas, Nikolaos, Ma, Jie, John, Neha Anna, Doss, Srikanth, Marquez, Lluis, Ballesteros, Miguel, Benajiba, Yassine
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Inference time LLM alignment in single and multidomain preference spectrum
by: Shahriar, Sadat, et al.
Published: (2024)

Diable: Efficient Dialogue State Tracking as Operations on Tables
by: Lesci, Pietro, et al.
Published: (2023)

Active Evaluation Acquisition for Efficient LLM Benchmarking
by: Li, Yang, et al.
Published: (2024)

Arabic Named Entity Recognition
by: Yassine Benajiba
Published: (2010)

Towards Long Context Hallucination Detection
by: Liu, Siyi, et al.
Published: (2025)

General Purpose Verification for Chain of Thought Prompting
by: Vacareanu, Robert, et al.
Published: (2024)

Capturing Gaze Shifts for Guidance: Cross-Modal Fusion Enhancement for VLM Hallucination Mitigation
by: Qi, Zheng, et al.
Published: (2025)

Balancing Classification and Calibration Performance in Decision-Making LLMs via Calibration Aware Reinforcement Learning
by: Yaldiz, Duygu Nur, et al.
Published: (2026)

From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification
by: Wang, Fei, et al.
Published: (2024)

Rethinking LLM Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model Uncertainty
by: Feng, Yu, et al.
Published: (2024)

NewsQs: Multi-Source Question Generation for the Inquiring Mind
by: Hwang, Alyssa, et al.
Published: (2024)

Sequential Editing for Lifelong Training of Speech Recognition Models
by: Kulshreshtha, Devang, et al.
Published: (2024)

MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversation
by: Singh, Jyotika, et al.
Published: (2026)

Barriers to Discrete Reasoning with Transformers: A Survey Across Depth, Exactness, and Bandwidth
by: Yuan, Michelle, et al.
Published: (2026)

SQLSpace: A Representation Space for Text-to-SQL to Discover and Mitigate Robustness Gaps
by: Srikanth, Neha, et al.
Published: (2025)

NLI under the Microscope: What Atomic Hypothesis Decomposition Reveals
by: Srikanth, Neha, et al.
Published: (2025)

VLM-Guard: Safeguarding Vision-Language Models via Fulfilling Safety Alignment Gap
by: Liu, Qin, et al.
Published: (2025)

MemInsight: Autonomous Memory Augmentation for LLM Agents
by: Salama, Rana, et al.
Published: (2025)

Open Domain Question Answering with Conflicting Contexts
by: Liu, Siyi, et al.
Published: (2024)

Safety Alignment for Vision Language Models
by: Liu, Zhendong, et al.
Published: (2024)

Exploiting Data Significance in Remote Estimation of Discrete-State Markov Sources
by: Luo, Jiping, et al.
Published: (2024)

From AoI to QVAoI: Query-Based Semantics-Aware Scheduling for Energy-Harvesting IoT Systems
by: Delfani, Erfan, et al.
Published: (2024)

From Timestamps to Versions: Version AoI in Single- and Multi-Hop Networks
by: Delfani, Erfan, et al.
Published: (2025)

Real-Time Reconstruction and Actuation Error Analysis for Markov Sources over MPR Channels
by: Elessawy, Pansee S., et al.
Published: (2026)

Goal-oriented Estimation of Multiple Markov Sources in Resource-constrained Systems
by: Luo, Jiping, et al.
Published: (2023)

Semantics-Aware Updates from Remote Energy Harvesting Devices to Interconnected LEO Satellites
by: Delfani, Erfan, et al.
Published: (2025)

Semantic-Aware Remote Estimation of Multiple Markov Sources Under Constraints
by: Luo, Jiping, et al.
Published: (2024)

Computation-aware Energy-harvesting Federated Learning: Cyclic Scheduling with Selective Participation
by: Jeong, Eunjeong, et al.
Published: (2025)

Battery-aware Cyclic Scheduling in Energy-harvesting Federated Learning
by: Jeong, Eunjeong, et al.
Published: (2025)

On the Role of Age and Semantics of Information in Remote Estimation of Markov Sources
by: Luo, Jiping, et al.
Published: (2025)

Technology‐Enabled Competitiveness and Experiences in Tourism: A Transformative Era
by: Eleni Michopoulou, et al.
Published: (2025)

Computing the Exact Pareto Front in Average-Cost Multi-Objective Markov Decision Processes
by: Luo, Jiping, et al.
Published: (2026)

Optimizing Version AoI in Energy-Harvesting IoT: Model-Based and Learning-Based Approaches
by: Delfani, Erfan, et al.
Published: (2025)

On the Cost of Consecutive Estimation Error: Significance-Aware Non-linear Aging
by: Luo, Jiping, et al.
Published: (2024)

Joint Accuracy and Confidentiality in Semantic-Aware Secure Remote Reconstruction
by: Li, Bowen, et al.
Published: (2026)

Optimizing Information Freshness in IoT Systems with Update Rate Constraints: A Token-Based Approach
by: Delfani, Erfan, et al.
Published: (2024)

Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment
by: Xue, Zhiyu, et al.
Published: (2026)

Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!
by: Zhou, Zhanhui, et al.
Published: (2024)

Understanding and Improving Information Preservation in Prompt Compression for LLMs
by: Łajewska, Weronika, et al.
Published: (2025)

Watermarking Degrades Alignment in Language Models: Analysis and Mitigation
by: Verma, Apurv, et al.
Published: (2025)