@inproceedings{choi-etal-2026-finharmbench,
    title = "{F}in{H}arm{B}ench: Financial Jailbreak Benchmark and Unsupervised Safety Fine-Tuning via Refusal Steering Distillation",
    author = "Choi, Yubin  and
      Yang, Yujin  and
      Kim, Subin  and
      Ham, Seokil  and
      Cho, Seungju  and
      Son, Jungmin  and
      Kwak, Youngjun  and
      Kim, Changick",
    editor = "Li, Yunyao  and
      Rehm, Georg  and
      Tu, Mei",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-industry.117/",
    pages = "1714--1726",
    ISBN = "979-8-89176-394-4",
    abstract = "Financial Large Language Models (LLMs) exhibit strong domain expertise but remain vulnerable to financially harmful prompts. To systematically assess this vulnerability, we introduce \textbf{FinHarmBench}, a benchmark designed to evaluate financially harmful and confusable benign prompts. Our analysis reveals a concerning result that financial LLMs can be less robust than general-purpose models, suggesting that domain adaptation alone does not guarantee financial safety alignment. To address this issue, we propose \textbf{Financial Refusal Steering Distillation (FiRSD)}, an unsupervised training framework that strengthens financial-domain safety by learning and distilling a financial refusal direction at the representation level. FiRSD enhances refusal behavior without requiring annotated refusal responses. Experiments show that FiRSD substantially improves safety while largely preserving task capability. These results highlight the importance of domain-aware safety alignment for high-stakes financial applications."
}