Cover Image

Towards Context-Invariant Safety Alignment for Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Yixu, Yao, Yang, Wang, Xin, Gao, Yifeng, Teng, Yan, Ma, Xingjun, Wang, Yingchun
Format:	Preprint
Published:	2026
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

SafeVid: Toward Safety Aligned Video Large Multimodal Models
by: Wang, Yixu, et al.
Published: (2025)

AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models
by: Wang, Yixu, et al.
Published: (2025)

Probing the Robustness of Large Language Models Safety to Latent Perturbations
by: Gu, Tianle, et al.
Published: (2025)

Fake Alignment: Are LLMs Really Aligned Well?
by: Wang, Yixu, et al.
Published: (2023)

LinguaSafe: A Comprehensive Multilingual Safety Benchmark for Large Language Models
by: Ning, Zhiyuan, et al.
Published: (2025)

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

SentGuard: Sentence-Level Streaming Guardrails for Large Language Models
by: Yu, Jiaqi, et al.
Published: (2026)

A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos
by: Yao, Yang, et al.
Published: (2025)

Mechanistic Origin of Moral Indifference in Language Models
by: Li, Lingyu, et al.
Published: (2026)

Argus Inspection: Do Multimodal Large Language Models Possess the Eye of Panoptes?
by: Yao, Yang, et al.
Published: (2025)

IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves
by: Wang, Ruofan, et al.
Published: (2024)

Internal Safety Collapse in Frontier Large Language Models
by: Wu, Yutao, et al.
Published: (2026)

Flames: Benchmarking Value Alignment of LLMs in Chinese
by: Huang, Kexin, et al.
Published: (2023)

CALM: Curiosity-Driven Auditing for Large Language Models
by: Zheng, Xiang, et al.
Published: (2025)

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

MESA: Improving MoE Safety Alignment via Decentralized Expertise
by: Sun, Yitong, et al.
Published: (2026)

Dr. Bench: A Multidimensional Evaluation for Deep Research Agents, from Answers to Reports
by: Yao, Yang, et al.
Published: (2025)

Identity Lock: Locking API Fine-tuned LLMs With Identity-based Wake Words
by: Su, Hongyu, et al.
Published: (2025)

Imperceptible Jailbreaking against Large Language Models
by: Gao, Kuofeng, et al.
Published: (2025)

The Other Mind: How Language Models Exhibit Human Temporal Cognition
by: Li, Lingyu, et al.
Published: (2025)

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation
by: Zhang, Zhibo, et al.
Published: (2025)

MEOW: MEMOry Supervised LLM Unlearning Via Inverted Facts
by: Gu, Tianle, et al.
Published: (2024)

EnJa: Ensemble Jailbreak on Large Language Models
by: Zhang, Jiahao, et al.
Published: (2024)

Special Characters Attack: Toward Scalable Training Data Extraction From Large Language Models
by: Bai, Yang, et al.
Published: (2024)

Reflection-Bench: Evaluating Epistemic Agency in Large Language Models
by: Li, Lingyu, et al.
Published: (2024)

Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
by: Chen, Yunhao, et al.
Published: (2025)

Unforgotten Safety: Preserving Safety Alignment of Large Language Models with Continual Learning
by: Alssum, Lama, et al.
Published: (2025)

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

DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models
by: Sun, Ye, et al.
Published: (2026)

Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models
by: Lin, Hongzhan, et al.
Published: (2024)

Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application
by: Yang, Chuanpeng, et al.
Published: (2024)

StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data
by: Wang, Yixu, et al.
Published: (2025)

Do Large Language Models Understand Logic or Just Mimick Context?
by: Yan, Junbing, et al.
Published: (2024)

Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
by: Chen, Jianhui, et al.
Published: (2024)

Safety Evaluation of DeepSeek Models in Chinese Contexts
by: Zhang, Wenjing, et al.
Published: (2025)

RedTopic: Toward Topic-Diverse Red Teaming of Large Language Models
by: Ding, Jiale, et al.
Published: (2025)

Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models
by: Wang, Teng, et al.
Published: (2025)

Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model
by: Wang, Siyin, et al.
Published: (2024)

Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment
by: Wang, Haoran, et al.
Published: (2023)

Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models
by: Wang, Fei, et al.
Published: (2024)