cs.CLNov 12, 2026

Data-Efficient LLM Safety Alignment Guided by Interpretable Features

Authors: Hongyu Li, Zhan Yu, Zhe Zhao, Kimmo Yan, Xiong Kuang, Renfen Hu

Organizations: Beijing Normal University · Tencent Beijing,China

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.

Figures & tables

Appendix figures & tables32 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Beyond Refusal Patterns: Safe-Role Internalization for Robust and Generalizable LLM Safety Alignment

    Oct 4, 2026Jinghao Pang, Jitai Hao, Qiang Huang +2LLM AlignmentLLM Safety Alignment

  2. SafeEvo: Deciphering the Safety Alignment Mechanism and Evolution in Language Models

    Oct 7, 2026Miao Yu, Hao Huang, Lu Yuan +3Refusal Mechanisms in Language ModelsLLM Safety Alignment

  3. PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models

    Jun 24, 2026Chang Wu, Junfeng Fang, Houcheng Jiang +5LLM AlignmentLLM Safety Alignment