Cover Image

SGM: Safety Glasses for Multimodal Large Language Models via Neuron-Level Detoxification

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Hongbo, AprilPyone, MaungMaung, Echizen, Isao
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Stability Analysis of ChatGPT-based Sentiment Analysis in AI Quality Assurance
by: Ouyang, Tinghui, et al.
Published: (2024)

Fine-Tuning Text-To-Image Diffusion Models for Class-Wise Spurious Feature Generation
by: MaungMaung, AprilPyone, et al.
Published: (2024)

EditSleuth: A Dataset of Grounded Reasoning Chains for Image-Edit Forensics
by: Nguyen, Van-Loc, et al.
Published: (2026)

Beyond Standard Benchmarks: A Systematic Audit of Vision-Language Model's Robustness to Natural Semantic Variation Across Diverse Tasks
by: Chengyu, Jia, et al.
Published: (2026)

Mitigating Backdoor Attacks using Activation-Guided Model Editing
by: Hsieh, Felix, et al.
Published: (2024)

Cross-Attention Watermarking of Large Language Models
by: Baldassini, Folco Bertini, et al.
Published: (2024)

Zero-Shot Warning Generation for Misinformative Multimodal Content
by: Delvecchio, Giovanni Pio, et al.
Published: (2025)

LLMD: A Large Language Model for Interpreting Longitudinal Medical Records
by: Porter, Robert, et al.
Published: (2024)

Detoxification of Large Language Models through Output-layer Fusion with a Calibration Model
by: Tian, Yuanhe, et al.
Published: (2025)

Cleansing the Artificial Mind: A Self-Reflective Detoxification Framework for Large Language Models
by: Zhang, Kaituo, et al.
Published: (2026)

Leveraging Chat-Based Large Vision Language Models for Multimodal Out-Of-Context Detection
by: Shalabi, Fatma, et al.
Published: (2024)

Image-Text Out-Of-Context Detection Using Synthetic Multimodal Misinformation
by: Shalabi, Fatma, et al.
Published: (2024)

CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification
by: Wang, Yian, et al.
Published: (2026)

Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification?
by: Lin, Fei, et al.
Published: (2025)

Enhancing Robustness of LLM-Synthetic Text Detectors for Academic Writing: A Comprehensive Analysis
by: Dou, Zhicheng, et al.
Published: (2024)

On the Role of Artificial Intelligence in Human-Machine Symbiosis
by: Chang, Ching-Chun, et al.
Published: (2026)

Steering Multimodal Large Language Models Decoding for Context-Aware Safety
by: Liu, Zheyuan, et al.
Published: (2025)

A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
by: Kazemi, Hamid, et al.
Published: (2026)

DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion
by: Li, Yu, et al.
Published: (2024)

SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models
by: Torres-Fonseca, Josue, et al.
Published: (2026)

Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-Judge
by: Sun, Xin, et al.
Published: (2026)

Decision-Level Ordinal Modeling for Multimodal Essay Scoring with Large Language Models
by: Zhang, Han, et al.
Published: (2026)

On Adversarial Robustness and Out-of-Distribution Robustness of Large Language Models
by: Yang, April, et al.
Published: (2024)

Enhancing Safety of Large Language Models via Embedding Space Separation
by: Zhao, Xu, et al.
Published: (2026)

EmoBench-M: Benchmarking Emotional Intelligence for Multimodal Large Language Models
by: Hu, He, et al.
Published: (2025)

MLLM-CL: Continual Learning for Multimodal Large Language Models
by: Zhao, Hongbo, et al.
Published: (2025)

Multimodal Adversarial Defense for Vision-Language Models by Leveraging One-To-Many Relationships
by: Waseda, Futa, et al.
Published: (2024)

Measuring Human Involvement in AI-Generated Text: A Case Study on Academic Writing
by: Guo, Yuchen, et al.
Published: (2025)

LongSafety: Evaluating Long-Context Safety of Large Language Models
by: Lu, Yida, et al.
Published: (2025)

Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons
by: Wang, Yifei, et al.
Published: (2024)

MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues
by: Liu, Zheyuan, et al.
Published: (2026)

Towards Safety and Helpfulness Balanced Responses via Controllable Large Language Models
by: Tuan, Yi-Lin, et al.
Published: (2024)

Parameter-Efficient Detoxification with Contrastive Decoding
by: Niu, Tong, et al.
Published: (2024)

Multilingual and Explainable Text Detoxification with Parallel Corpora
by: Dementieva, Daryna, et al.
Published: (2024)

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

Revisiting Large Language Model Pruning using Neuron Semantic Attribution
by: Ding, Yizhuo, et al.
Published: (2025)

Defending Large Language Models Against Jailbreak Attacks via In-Decoding Safety-Awareness Probing
by: Zhao, Yinzhi, et al.
Published: (2026)

MultiParaDetox: Extending Text Detoxification with Parallel Data to New Languages
by: Dementieva, Daryna, et al.
Published: (2024)

Towards Context-Invariant Safety Alignment for Large Language Models
by: Wang, Yixu, et al.
Published: (2026)

MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
by: Gu, Tianle, et al.
Published: (2024)