@inproceedings{in-etal-2025-safety,
    title = "Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models",
    author = "In, Yeonjun  and
      Kim, Wonjoong  and
      Yoon, Kanghoon  and
      Kim, Sungchul  and
      Tanjim, Mehrab  and
      Park, Sangwu  and
      Kim, Kibum  and
      Park, Chanyoung",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.353/",
    doi = "10.18653/v1/2025.findings-emnlp.353",
    pages = "6652--6671",
    ISBN = "979-8-89176-335-7",
    abstract = "As the use of large language model (LLM) agents continues to grow, their safety vulnerabilities have become increasingly evident. Extensive benchmarks evaluate various aspects of LLM safety by defining the safety relying heavily on general standards, overlooking user-specific standards. However, safety standards for LLM may vary based on a user-specific profiles rather than being universally consistent across all users. This raises a critical research question: Do LLM agents act safely when considering user-specific safety standards? Despite its importance for safe LLM use, no benchmark datasets currently exist to evaluate the user-specific safety of LLMs. To address this gap, we introduce U-SafeBench, a benchmark designed to assess user-specific aspect of LLM safety. Our evaluation of 20 widely used LLMs reveals current LLMs fail to act safely when considering user-specific safety standards, marking a new discovery in this field. To address this vulnerability, we propose a simple remedy based on chain-of-thought, demonstrating its effectiveness in improving user-specific safety."
}