@inproceedings{hou-etal-2026-finsafetybench,
    title = "{F}in{S}afety{B}ench: Evaluating {LLM} Safety in Real-World Financial Scenarios",
    author = "Hou, Yutao  and
      Jiang, Yihan  and
      Xie, Yuhan  and
      Yang, Jian  and
      Zhang, Liwen  and
      Huang, Hailiang  and
      Chen, Guanhua  and
      Chen, Yun",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.694/",
    pages = "14181--14208",
    ISBN = "979-8-89176-395-1",
    abstract = "Large language models (LLMs) are increasingly applied in financial scenarios. However, they may produce harmful outputs, including facilitating illegal activities or unethical behavior, posing serious compliance risks. To systematically evaluate LLM safety in finance, we propose FinSafetyBench, a bilingual (English-Chinese) red-teaming benchmark designed to test an LLM{'}s refusal of requests that violate financial compliance. Grounded in real-world financial crime cases and ethics standards, the benchmark comprises 14 subcategories spanning financial crimes and ethical violations. Through extensive experiments on general-purpose and finance-specialized LLMs under three representative attack settings, we identify critical vulnerabilities that allow adversarial prompts to bypass compliance safeguards. Further analysis reveals stronger susceptibility in Chinese contexts and highlights the limitations of prompt-level defenses against sophisticated or implicit manipulation strategies."
}