Less is Safer：基于可解释特征的数据高效 LLM 安全对齐方法
Data-Efficient LLM Safety Alignment Guided by Interpretable Features
AI 导读
一项 arXiv 研究提出 Less is Safer（LIS），通过 Sparse Autoencoder（SAE）激活筛选可解释安全特征，并结合多智能体对抗合成，构建仅 2.4K 样本的安全对齐数据集。
正文 · 原文
Abstract:Existing large language models typically rely on massive fine-tuning datasets for safety alignment, which results in higher costs for safety alignment and often leads to the problem of over-refusal. We propose Less is Safer (LIS), a compact yet highly effective dataset for safety alignment, constructed through interpretable feature-guided selection and adversarial synthesis. Specifically, we leverage Sparse Autoencoder (SAE) activations to efficiently select prompts that cover diverse and interpretable safety features. Then, we employ a multi-agent adversarial synthesis framework to generate harmless prompts that nevertheless elicit unnecessary refusals. LIS contains only 2.4K samples, yet outperforms much larger datasets, e.g., TRIDENT-Core (26K), TRIDENT-Edge (19K) and WildJailbreak (262K), in overall performance on four safety and five over-refusal benchmarks. Through ablation experiments, we demonstrate that neither safety data nor over-refusal data alone can achieve optimal results. We also used safety features from SAE, annotated by an LLM, for data filtering, but the results were inferior to those obtained using the pipeline proposed in this paper.
| Comments: | 36 pages, 16 figures |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.16183 [cs.CL] |
| (or arXiv:2611.16183v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.16183 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hongyu Li [view email]
[v1]
Thu, 12 Nov 2026 02:15:45 UTC (3,750 KB)
来源：arXiv cs.AI · arxiv.org