@inproceedings{rebedea-etal-2025-guardrails,
    title = "Guardrails and Security for {LLM}s: Safe, Secure and Controllable Steering of {LLM} Applications",
    author = "Rebedea, Traian  and
      Derczynski, Leon  and
      Ghosh, Shaona  and
      Sreedhar, Makesh Narsimhan  and
      Brahman, Faeze  and
      Jiang, Liwei  and
      Li, Bo  and
      Tsvetkov, Yulia  and
      Parisien, Christopher  and
      Choi, Yejin",
    editor = "Arase, Yuki  and
      Jurgens, David  and
      Xia, Fei",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 5: Tutorial Abstracts)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-tutorials.8/",
    pages = "13--15",
    ISBN = "979-8-89176-255-8",
    abstract = "Pretrained generative models, especially large language models, provide novel ways for users to interact with computers. While generative NLP research and applications had previously aimed at very domain-specific or task-specific solutions, current LLMs and applications (e.g. dialogue systems, agents) are versatile across many tasks and domains. Despite being trained to be helpful and aligned with human preferences (e.g., harmlessness), enforcing robust guardrails on LLMs remains a challenge. And, even when protected against rudimentary attacks, just like other complex software, LLMs can be vulnerable to attacks using sophisticated adversarial inputs. This tutorial provides a comprehensive overview of key guardrail mechanisms developed for LLMs, along with evaluation methodologies and a detailed security assessment protocol - including auto red-teaming of LLM-powered applications. Our aim is to move beyond the discussion of single prompt attacks and evaluation frameworks towards addressing how guardrailing can be done in complex dialogue systems that employ LLMs."
}