Hugging Face Trending Papers July 13, 2026

HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models

Read the original on Hugging Face Trending Papers →

Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance. Existing defenses mainly follow two directions: they either intervene during or after fine-tuning through retraining or weight modification, which can be costly and may hurt task performance, or they use model-agnostic safety classifiers, which may miss failures specific to a given fine-tuned checkpoint.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning

Jul 14

HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models

arXiv:2607. 11475v1 Announce Type: new Abstract: Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance.

By Aznaur Aliev, Carlos Hinojosa, Abdelrahman Eldesokey, Bang An, Bernard Ghanem, Yibo Yang

llms fine-tuning benchmarks safety

arXiv AI

Jul 21

TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment

arXiv:2607. 16242v1 Announce Type: cross Abstract: Fine-Tuning-as-a-Service (FTaaS) platforms let users train large language models (LLMs) on customized tasks, but this pipeline could erode models' safety alignment.

By Changyue Li, Jiaming He, Youliang Yuan, Jialin Wu, Boxi Yu, Zhicong Huang, Pinjia He

llms fine-tuning benchmarks 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 8

SafeGene: Reusable Adapters for Transferable Safety Alignment

arXiv:2606. 06519v1 Announce Type: new Abstract: Open-weight LLMs are increasingly fine-tuned into customized assistants, but downstream fine-tuning can weaken safety alignment and make models more vulnerable to malicious prompts, even when the training data is not intentionally harmful.

By Yanghan Wang, Zhiqiang Kou, Fu Feng, Jing Wang, Xin Geng

llms fine-tuning 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 AI

Jun 10

Stop Early, Spend Less: Hidden-State Probes as a Practical Recipe for Streaming Moderation of LLM Outputs

arXiv:2606. 10487v1 Announce Type: cross Abstract: Deploying large language models in user-facing systems requires efficient output safety filtering.

By Huizhen Shu, Xuying Li, Piao Xue

llms safety

Related stories

HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models

TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment

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

SafeGene: Reusable Adapters for Transferable Safety Alignment

NeST: Neuron Selective Tuning for LLM Safety

Stop Early, Spend Less: Hidden-State Probes as a Practical Recipe for Streaming Moderation of LLM Outputs