@inproceedings{dasgupta-etal-2026-arrest,
    title = "{ARREST}: Adversarial Resilient Regulation Enhancing Safety and Truth in Large Language Models",
    author = "Dasgupta, Sharanya  and
      Basu, Arkaprabha  and
      Nath, Sujoy  and
      Das, Swagatam",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-long.212/",
    pages = "4565--4584",
    ISBN = "979-8-89176-380-7",
    abstract = "Human cognition, driven by complex neurochemical processes, oscillates between imagination and reality and learns to self-correct whenever such subtle drifts lead to hallucinations or unsafe associations. In recent years, Large Language Models (LLMs) have demonstrated remarkable performance in a wide range of tasks. However, they still lack human cognition to balance factuality and safety. Bearing the resemblance, we argue that both factual and safety failures in LLMs arise from a common underlying issue, ``representational misalignment'' in their latent activation space. We hypothesize that an external network, trained to understand the fluctuations, can selectively intervene in the model to regulate falsehood into truthfulness and unsafe output into safe output without fine-tuning the LLM{'}s parameters. Reflecting the hypothesis, we propose ARREST (Adversarial Resilient Regulation Enhancing Safety and Truth), a unified framework that identifies and corrects drifted features, engaging both soft and hard refusals in addition to factual corrections. Our empirical results show that ARREST not only regulates misalignment but is also more versatile compared to the Reinforcement Learning from Human Feedback (RLHF)-aligned models in generating soft refusals due to adversarial training. We make our codebase available at https://github.com/sharanya-dasgupta001/ARREST."
}