<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dabiriaghdam-wang-2025-simmark">
    <titleInfo>
        <title>SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Amirhossein</namePart>
        <namePart type="family">Dabiriaghdam</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lele</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Violet</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-332-6</identifier>
    </relatedItem>
    <abstract>The widespread adoption of large language models (LLMs) necessitates reliable methods to detect LLM-generated text. We introduce SimMark, a robust sentence-level watermarking algorithm that makes LLMs’ outputs traceable without requiring access to model internals, making it compatible with both open and API-based LLMs. By leveraging the similarity of semantic sentence embeddings combined with rejection sampling to embed detectable statistical patterns imperceptible to humans, and employing a soft counting mechanism, SimMark achieves robustness against paraphrasing attacks. Experimental results demonstrate that SimMark sets a new benchmark for robust watermarking of LLM-generated content, surpassing prior sentence-level watermarking techniques in robustness, sampling efficiency, and applicability across diverse domains, all while maintaining the text quality and fluency.</abstract>
    <identifier type="citekey">dabiriaghdam-wang-2025-simmark</identifier>
    <identifier type="doi">10.18653/v1/2025.emnlp-main.1567</identifier>
    <location>
        <url>https://aclanthology.org/2025.emnlp-main.1567/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>30785</start>
            <end>30806</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Models
%A Dabiriaghdam, Amirhossein
%A Wang, Lele
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F dabiriaghdam-wang-2025-simmark
%X The widespread adoption of large language models (LLMs) necessitates reliable methods to detect LLM-generated text. We introduce SimMark, a robust sentence-level watermarking algorithm that makes LLMs’ outputs traceable without requiring access to model internals, making it compatible with both open and API-based LLMs. By leveraging the similarity of semantic sentence embeddings combined with rejection sampling to embed detectable statistical patterns imperceptible to humans, and employing a soft counting mechanism, SimMark achieves robustness against paraphrasing attacks. Experimental results demonstrate that SimMark sets a new benchmark for robust watermarking of LLM-generated content, surpassing prior sentence-level watermarking techniques in robustness, sampling efficiency, and applicability across diverse domains, all while maintaining the text quality and fluency.
%R 10.18653/v1/2025.emnlp-main.1567
%U https://aclanthology.org/2025.emnlp-main.1567/
%U https://doi.org/10.18653/v1/2025.emnlp-main.1567
%P 30785-30806

Markdown (Informal)

[SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Models](https://aclanthology.org/2025.emnlp-main.1567/) (Dabiriaghdam & Wang, EMNLP 2025)

• SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Models (Dabiriaghdam & Wang, EMNLP 2025)

ACL

• Amirhossein Dabiriaghdam and Lele Wang. 2025. SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Models. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 30785–30806, Suzhou, China. Association for Computational Linguistics.