@inproceedings{li-etal-2025-llm,
    title = "{LLM}-Generated Passphrases That Are Secure and Easy to Remember",
    author = "Li, Jie S.  and
      Geiping, Jonas  and
      Goldblum, Micah  and
      Saha, Aniruddha  and
      Goldstein, Tom",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.findings-naacl.290/",
    pages = "5216--5234",
    ISBN = "979-8-89176-195-7",
    abstract = "Automatically generated passwords and passphrases are a cornerstone of IT security. Yet, these passphrases are often hard to remember and see only limited adoption. In this work, we use large language models to generate passphrases with rigorous security guarantees via the computation of the entropy of the output as a metric of the security of the passphrase. We then present a range of practical methods to generate language model outputs with sufficient entropy: raising entropy through in-context examples and generation through a new top-q truncation method. We further verify the influence of prompt construction in steering the output topic and grammatical structure. Finally, we conduct user studies to determine the adoption rates for these LLM-generated passphrases in practice."
}