Cover Image

Multilingual Safety Alignment via Self-Distillation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Qin, Ruiyang, Wang, Qingzhuo, Liu, Dongrui, Li, Qiang, Wei, Zhihua, Shen, Wen
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment
by: Bu, Yuyan, et al.
Published: (2026)

COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation
by: Zhou, Tianyi, et al.
Published: (2026)

SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models
by: Chuang, Yung-Sung, et al.
Published: (2025)

Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
by: Shen, Guobin, et al.
Published: (2026)

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

Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
by: Wei, Boyi, et al.
Published: (2024)

Safety Reasoning with Guidelines
by: Wang, Haoyu, et al.
Published: (2025)

GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation
by: Li, Sijia, et al.
Published: (2026)

Spatial Distillation based Distribution Alignment (SDDA) for Cross-Headset EEG Classification
by: Liu, Dingkun, et al.
Published: (2025)

Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models
by: Liu, Qin, et al.
Published: (2024)

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

Self-Distilled Agentic Reinforcement Learning
by: Lu, Zhengxi, et al.
Published: (2026)

Course-Correction: Safety Alignment Using Synthetic Preferences
by: Xu, Rongwu, et al.
Published: (2024)

Lifelong Safety Alignment for Language Models
by: Wang, Haoyu, et al.
Published: (2025)

SDMPrune: Self-Distillation MLP Pruning for Efficient Large Language Models
by: Zhu, Hourun, et al.
Published: (2025)

Self-Distillation for Multi-Token Prediction
by: Zhao, Guoliang, et al.
Published: (2026)

Evolutionary Contrastive Distillation for Language Model Alignment
by: Katz-Samuels, Julian, et al.
Published: (2024)

HLL: Can Agents Cross Humanity's Last Line of Verification?
by: Song, Xinhao, et al.
Published: (2026)

Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation
by: Wang, Dianyun, et al.
Published: (2025)

Test-Time Safety Alignment
by: Saglam, Baturay, et al.
Published: (2026)

CARE: Decoding Time Safety Alignment via Rollback and Introspection Intervention
by: Hu, Xiaomeng, et al.
Published: (2025)

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

AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation
by: Zhang, Songming, et al.
Published: (2025)

SALMON: Self-Alignment with Instructable Reward Models
by: Sun, Zhiqing, et al.
Published: (2023)

Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
by: Wang, Hao, et al.
Published: (2026)

Post-Trained MoE Can Skip Half Experts via Self-Distillation
by: Lv, Xingtai, et al.
Published: (2026)

Confidence-aware Self-Semantic Distillation on Knowledge Graph Embedding
by: Liu, Yichen, et al.
Published: (2022)

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

Reasoning Distillation and Structural Alignment for Improved Code Generation
by: Jalilifard, Amir, et al.
Published: (2025)

Merge-of-Thought Distillation
by: Shen, Zhanming, et al.
Published: (2025)

Latent Context Compilation: Distilling Long Context into Compact Portable Memory
by: Li, Zeju, et al.
Published: (2026)

The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm
by: Aakanksha, et al.
Published: (2024)

SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders
by: Yu, Zhuohao, et al.
Published: (2025)

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
by: Yang, Junxiao, et al.
Published: (2026)

Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment
by: Wang, Haowen, et al.
Published: (2025)

Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion
by: Tan, Zhen, et al.
Published: (2026)

Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection
by: Shairah, Harethah Abu, et al.
Published: (2025)

Picky LLMs and Unreliable RMs: An Empirical Study on Safety Alignment after Instruction Tuning
by: Li, Guanlin, et al.
Published: (2025)

Feature Structure Distillation with Centered Kernel Alignment in BERT Transferring
by: Jung, Hee-Jun, et al.
Published: (2022)

Safety Alignment Can Be Not Superficial With Explicit Safety Signals
by: Li, Jianwei, et al.
Published: (2025)