<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-llm">
    <titleInfo>
        <title>LLM-Generated Passphrases That Are Secure and Easy to Remember</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jie</namePart>
        <namePart type="given">S</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jonas</namePart>
        <namePart type="family">Geiping</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Micah</namePart>
        <namePart type="family">Goldblum</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aniruddha</namePart>
        <namePart type="family">Saha</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tom</namePart>
        <namePart type="family">Goldstein</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-04</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Luis</namePart>
            <namePart type="family">Chiruzzo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alan</namePart>
            <namePart type="family">Ritter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lu</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Albuquerque, New Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-195-7</identifier>
    </relatedItem>
    <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.</abstract>
    <identifier type="citekey">li-etal-2025-llm</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-naacl.290</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-naacl.290/</url>
    </location>
    <part>
        <date>2025-04</date>
        <extent unit="page">
            <start>5216</start>
            <end>5234</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T LLM-Generated Passphrases That Are Secure and Easy to Remember
%A Li, Jie S.
%A Geiping, Jonas
%A Goldblum, Micah
%A Saha, Aniruddha
%A Goldstein, Tom
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F li-etal-2025-llm
%X 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.
%R 10.18653/v1/2025.findings-naacl.290
%U https://aclanthology.org/2025.findings-naacl.290/
%U https://doi.org/10.18653/v1/2025.findings-naacl.290
%P 5216-5234

Markdown (Informal)

[LLM-Generated Passphrases That Are Secure and Easy to Remember](https://aclanthology.org/2025.findings-naacl.290/) (Li et al., Findings 2025)

• LLM-Generated Passphrases That Are Secure and Easy to Remember (Li et al., Findings 2025)

ACL

• Jie S. Li, Jonas Geiping, Micah Goldblum, Aniruddha Saha, and Tom Goldstein. 2025. LLM-Generated Passphrases That Are Secure and Easy to Remember. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 5216–5234, Albuquerque, New Mexico. Association for Computational Linguistics.