@inproceedings{halloran-2026-understanding,
    title = "Understanding the Effects of Safety Unalignment on Reasoning- and Instruction-Tuned Large Language Models",
    author = "Halloran, John Timothy",
    editor = "Chang, Kai-Wei  and
      Mehrabi, Ninareh  and
      Krishna, Satyapriya  and
      Das, Anubrata  and
      Dhamala, Jwala  and
      Cao, Yang Trista  and
      Kumarage, Tharindu  and
      Ramakrishna, Anil  and
      Christodoulopoulos, Christos  and
      Wan, Yixin  and
      Galystan, Aram  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 6th Workshop on Trustworthy {NLP} ({T}rust{NLP} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.trustnlp-main.20/",
    pages = "330--341",
    ISBN = "979-8-89176-418-7",
    abstract = "Alignment has become a critical step towards enabling large language model (LLM) safety guardrails which ensure models provide helpful and harmless responses, while refusing malicious and harmful requests. However, two separate lines of recent work{--}unalignment via fine-tuning, i.e., jailbreak-tuning (JT), and weight orthogonalization (WO){--}have shown that LLM guardrails may be circumvented, such that LLMs obey harmful requests which they would normally refuse. Despite the safety implications of such unalignment procedures, a comprehensive analysis directly contrasting these methods is currently lacking, as is a study of these methods' impact on malicious LLM capabilities and reasoning models. Using both JT and WO, we study the impact of unaligning six popular LLMs{--}three reasoning LLMs of various sizes and their instruction-tuned analogues{--}across harmful safety tasks. Compared to JT, we show that WO produces models which are more effective at adversarially attacking LLMs{--}in particular, WO reasoning LLMs excel at such adversarial attacks. Interestingly, while increasing adversarial attack efficacy, we show that WO does not drastically increase hallucination rates. This is in stark contrast to JT, which may more than double the hallucination rate of both reasoning and instruction-tuned models alike. Finally, we show that off-the-shelf supervised fine-tuning effectively limits the adversarial attack abilities enabled by WO, without drastically increasing hallucination rates."
}