Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings

This study presents the first comprehensive safety evaluation of the DeepSeek models, focusing on evaluating the safety risks associated with their generated content. Our evaluation encompasses DeepSeek's latest generation of large language models, multimodal large language models, and text-to-image models, systematically examining their performance regarding unsafe content generation. Notably, we developed a bilingual (Chinese-English) safety evaluation dataset tailored to Chinese sociocultural contexts, enabling a more thorough evaluation of the safety capabilities of Chinese-developed models. Experimental results indicate that despite their strong general capabilities, DeepSeek models exhibit significant safety vulnerabilities across multiple risk dimensions, including algorithmic discrimination and sexual content. These findings provide crucial insights for understanding and improving the safety of large foundation models. Our code is available atthis https URL.
View on arXiv@article{ying2025_2503.15092, title={ Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings }, author={ Zonghao Ying and Guangyi Zheng and Yongxin Huang and Deyue Zhang and Wenxin Zhang and Quanchen Zou and Aishan Liu and Xianglong Liu and Dacheng Tao }, journal={arXiv preprint arXiv:2503.15092}, year={ 2025 } }