arXiv Machine Learning July 30, 2026 By Yongjian Guo, Wanlun Ma, Lingyu Shen, Xi Xiao, Sheng Wen

On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment

Read the original on arXiv Machine Learning →

arXiv:2607. 27081v1 Announce Type: cross Abstract: Fine-tuning is the dominant paradigm for specializing large language models (LLMs), yet it exposes a critical vulnerability: malicious data providers can embed harmful behaviors into downstream corpora, creating models that retain professional skills while violating human values on demand.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 3

Safety Targeted Embedding Exploit via Refinement

arXiv:2607. 01859v1 Announce Type: new Abstract: Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching.

By Joshua Adrian Cahyono

llms rag safety

Hugging Face Trending Papers

Jul 2

Safety Targeted Embedding Exploit via Refinement

Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching. We show that this creates an epistemic gap in which models confidently generate harmful responses for inputs that fall outside the distribution of their safety training.

llms rag safety

arXiv Machine Learning

5d ago

HiRoute: Hierarchical Routed Prompt Tuning for Safety Alignment of Large Language Models

arXiv:2608. 12821v1 Announce Type: new Abstract: Large language models (LLMs) remain vulnerable to harmful requests and jailbreak attacks.

By Fangzhou Chen, Shiji Zhao, Mengyang Wang, Qihui Zhu, Ranjie Duan, Maoxun Yuan, Xingxing Wei

llms rag benchmarks safety

arXiv AI

Jun 19

The Autonomy Tax: Defense Training Breaks LLM Agents

arXiv:2603. 19423v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks.

By Shawn Li, Yue Zhao

llms agents benchmarks safety

arXiv AI

Jul 1

A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems

arXiv:2606. 31639v1 Announce Type: cross Abstract: Large language models are no longer only text generators.

By Seyed Bagher Hashemi Natanzi, Bo Tang

llms agents robotics safety

arXiv AI

Aug 7

One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs

arXiv:2512. 14751v3 Announce Type: replace-cross Abstract: Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications.

By Yixin Tan, Zhe Yu, Rui Wen, Jun Sakuma

llms fine-tuning safety

Related stories

Safety Targeted Embedding Exploit via Refinement

Safety Targeted Embedding Exploit via Refinement

HiRoute: Hierarchical Routed Prompt Tuning for Safety Alignment of Large Language Models

The Autonomy Tax: Defense Training Breaks LLM Agents

A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems

One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs