@inproceedings{hung-etal-2026-gray,
    title = "Into the Gray Zone: Domain Contexts Can Blur {LLM} Safety Boundaries",
    author = "Hung, Ki Sen  and
      Yang, Xi  and
      Liu, Chang  and
      Li, Haoran  and
      Chen, Kejiang  and
      Fan, Changxuan  and
      Kwok, Tsun On  and
      Zhang, Weiming  and
      Li, Xiaomeng  and
      Song, Yangqiu",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1139/",
    pages = "24830--24867",
    ISBN = "979-8-89176-390-6",
    abstract = "A central goal of LLM alignment is to balance helpfulness with harmlessness, yet these objectives conflict when the same knowledge serves both legitimate and malicious purposes. This tension is amplified by context-sensitive alignment: we observe that domain-specific contexts (e.g., chemistry) selectively relax defenses for domain-relevant harmful knowledge, while safety-research contexts (e.g., jailbreak studies) trigger broader relaxation spanning all harm categories. To systematically exploit this vulnerability, we propose Jargon, a framework combining safety-research contexts with multi-turn adversarial interactions that achieves attack success rates exceeding 93{\%} across seven frontier models, including GPT-5.2, Claude-4.5, and Gemini-3, substantially outperforming existing methods. Activation space analysis reveals that Jargon queries occupy an intermediate region between benign and harmful inputs, a gray zone where refusal decisions become unreliable. To mitigate this vulnerability, we design a policy-guided safeguard that steers models toward helpful yet harmless responses, and internalize this capability through alignment fine-tuning, reducing attack success rates while preserving helpfulness."
}