arXiv Machine Learning June 9, 2026 By Motasem Alfarra, Cristina Pinneri, Dana Kianfar, Mohammed Almousa, Christos Louizos

Distilling Safe LLM Systems via Soft Prompts for On Device Settings

Read the original on arXiv Machine Learning →

arXiv:2606. 09388v1 Announce Type: new Abstract: Deploying safe large language models (LLMs) on resource-constrained edge devices presents a critical challenge: while dual-model systems combining LLMs with guard models provide effective safety guarantees, their substantial memory and computational demands make them prohibitively expensive for on-device deployment.

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

arXiv AI

Jun 2

SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment

arXiv:2606. 02530v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) with human values often degrades their general capabilities, termed the alignment tax.

By Hao Li, Jingkun An, Zijun Song, Pengyu Zhu, Rui Li, Hao Wang, Wendi Feng, Yesheng Liu, Lijun Li, Jin-Ge Yao, Lei Sha

llms efficiency benchmarks safety

arXiv Machine Learning

Jun 15

NeST: Neuron Selective Tuning for LLM Safety

arXiv:2602. 16835v2 Announce Type: replace-cross Abstract: Safety alignment is essential for the responsible deployment of Large Language Models (LLMs).

By Sasha Behrouzi, Lichao Wu, Mohamadreza Rostami, Ahmad-Reza Sadeghi

llms fine-tuning multimodal safety

arXiv Machine Learning

Jun 4

Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning

arXiv:2603. 07445v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data.

By Guoli Wang, Haonan Shi, Tu Ouyang, An Wang

llms fine-tuning safety

arXiv AI

Jun 6

Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation

arXiv:2606. 05290v1 Announce Type: cross Abstract: Recent progress in generative modeling has made safety control a central challenge, yet existing approaches remain largely model-specific, requiring retraining or tailored interventions for each new architecture.

By Tobia Poppi, Silvia Cappelletti, Sara Sarto, Florian Schiffers, Garin Kessler, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara

llms diffusion multimodal safety

arXiv AI

Jun 16

Adaptive and Explicit safe: Triggering Latent Safety Awareness in Large Reasoning Models

arXiv:2606. 16808v1 Announce Type: new Abstract: While Large Reasoning Models (LRMs) excel at complex tasks, they remain highly vulnerable to sophisticated jailbreaks and direct harmful queries.

By Ke Miao, Jiaxin Li, Hongliang Chen, Yuke Hu, Zhan Qin

llms reinforcement-learning fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Jun 11

AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin

arXiv:2506. 08473v4 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) improves performance but introduces critical safety vulnerabilities: even minimal harmful data can severely compromise safety measures.

By Shuo Yang, Qihui Zhang, Yuyang Liu, Xiaojun Jia, Kunpeng Ning, Jiayu Yao, Jigang Wang, Hailiang Dai, Yibing Song, Li Yuan

llms fine-tuning safety

Related stories

SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment

NeST: Neuron Selective Tuning for LLM Safety

Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning

Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation

Adaptive and Explicit safe: Triggering Latent Safety Awareness in Large Reasoning Models

AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin