← Back to all news
arXiv Computation and Language By Xu Zhao, Xiting Wang, Weiran Shen

Enhancing Safety of Large Language Models via Embedding Space Separation

Read the original on arXiv Computation and Language →

The paper proposes Embedding Space Separation (ES2), a fine‑tuning technique that increases the distance between harmful and harmless embeddings in large language models. ES2 uses two regularization losses—a embedding anchor loss and a KL‑divergence loss—to preserve the model’s general capabilities while enhancing safety. Experiments show that ES2 effectively defends against various attack methods with only modest performance loss on some tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

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.

llmsragsafety
More like this →
arXiv AI
Oct 28

TextCloak: Safeguarding Data from Unauthorized LLM Fine-Tuning via RL-Driven Unlearnable Examples

TextCloak is a reinforcement‑learning driven framework that generates unlearnable examples (UEs) to protect textual data from unauthorized fine‑tuning of large language models (LLMs). It transforms clean text into perturbations that preserve meaning and naturalness while degrading the utility of models trained on them. Experiments on six datasets and nine LLMs show that TextCloak consistently impairs unauthorized fine‑tuning and remains robust across different architectures, training settings, and adaptive attacks.

By Chengshuai Zhao, Pingchuan Ma, Dawei Li, Bohan Jiang, Zhiyuan Yu, Zhen Tan, Huan Liu
llmsreinforcement-learningfine-tuningbenchmarkssafety
More like this →
arXiv AI
Oct 1

Faithful Dual-constrained Erasure for Robust LLM Safety Alignment

The paper introduces FDCU, a dual‑constrained subspace projection framework designed to improve machine unlearning for large language models. FDCU limits parameter updates with a dual‑masking rule that preserves general knowledge via Fisher Information while preventing the activation of spurious suppressors through the Principle of Minimal Functional Intervention. Experiments show that FDCU achieves state‑of‑the‑art robustness against retraining attacks while maintaining near‑lossless general utility, thereby ensuring durable safety for LLMs.

By Jiaqing Li, Shide Zhou, Zhibo Zhang, Yuxi Li, Tianlong Yu, Kailong Wang
llmsfine-tuningbenchmarkssafety
More like this →