@inproceedings{hoang-etal-2026-spark,
title = "{S}p{ARK}: An Embarrassingly Simple Sparse Watermarking in {LLM}s with Enhanced Text Quality",
author = "Hoang, Duy Cao and
Le, Thanh Quoc Hung and
Chu, Rui and
Li, Ping and
Zhao, Weijie and
Lao, Yingjie and
Doan, Khoa D",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-eacl.240/",
pages = "4603--4626",
ISBN = "979-8-89176-386-9",
abstract = "With the widespread adoption of Large Language Models (LLMs), concerns about potential misuse have emerged. To this end, watermarking has been adapted to LLM, enabling a simple and effective way to detect and monitor generated text. However, while the existing methods can differentiate between watermarked and unwatermarked text with high accuracy, they often face a trade-off between the quality of the generated text and the effectiveness of the watermarking process. In this work, we present a novel type of LLM watermark, Sparse WatermARK (or SpARK), which aims to mitigate this trade-off by applying watermarks to a small subset of generated tokens distributed across the text. To demonstrate this type of watermark, we introduce two novel variants, SpARK-P and SpARK-R, which achieve sparsity by anchoring watermarked tokens to words that have specific Part-of-Speech (POS) tags and specific hash values w.r.t a pseudorandom hash function, respectively. Our experimental results demonstrate that the proposed watermarking schemes, albeit embarrassingly simple, are incredibly effective, achieving high detectability while generating text that outperforms previous LLM watermarking methods in quality across various tasks. SpARK further advances the watermarking capability for LLMs while maintaining their generated text quality."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hoang-etal-2026-spark">
<titleInfo>
<title>SpARK: An Embarrassingly Simple Sparse Watermarking in LLMs with Enhanced Text Quality</title>
</titleInfo>
<name type="personal">
<namePart type="given">Duy</namePart>
<namePart type="given">Cao</namePart>
<namePart type="family">Hoang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thanh</namePart>
<namePart type="given">Quoc</namePart>
<namePart type="given">Hung</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ping</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weijie</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingjie</namePart>
<namePart type="family">Lao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khoa</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Doan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-386-9</identifier>
</relatedItem>
<abstract>With the widespread adoption of Large Language Models (LLMs), concerns about potential misuse have emerged. To this end, watermarking has been adapted to LLM, enabling a simple and effective way to detect and monitor generated text. However, while the existing methods can differentiate between watermarked and unwatermarked text with high accuracy, they often face a trade-off between the quality of the generated text and the effectiveness of the watermarking process. In this work, we present a novel type of LLM watermark, Sparse WatermARK (or SpARK), which aims to mitigate this trade-off by applying watermarks to a small subset of generated tokens distributed across the text. To demonstrate this type of watermark, we introduce two novel variants, SpARK-P and SpARK-R, which achieve sparsity by anchoring watermarked tokens to words that have specific Part-of-Speech (POS) tags and specific hash values w.r.t a pseudorandom hash function, respectively. Our experimental results demonstrate that the proposed watermarking schemes, albeit embarrassingly simple, are incredibly effective, achieving high detectability while generating text that outperforms previous LLM watermarking methods in quality across various tasks. SpARK further advances the watermarking capability for LLMs while maintaining their generated text quality.</abstract>
<identifier type="citekey">hoang-etal-2026-spark</identifier>
<location>
<url>https://aclanthology.org/2026.findings-eacl.240/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>4603</start>
<end>4626</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SpARK: An Embarrassingly Simple Sparse Watermarking in LLMs with Enhanced Text Quality
%A Hoang, Duy Cao
%A Le, Thanh Quoc Hung
%A Chu, Rui
%A Li, Ping
%A Zhao, Weijie
%A Lao, Yingjie
%A Doan, Khoa D.
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F hoang-etal-2026-spark
%X With the widespread adoption of Large Language Models (LLMs), concerns about potential misuse have emerged. To this end, watermarking has been adapted to LLM, enabling a simple and effective way to detect and monitor generated text. However, while the existing methods can differentiate between watermarked and unwatermarked text with high accuracy, they often face a trade-off between the quality of the generated text and the effectiveness of the watermarking process. In this work, we present a novel type of LLM watermark, Sparse WatermARK (or SpARK), which aims to mitigate this trade-off by applying watermarks to a small subset of generated tokens distributed across the text. To demonstrate this type of watermark, we introduce two novel variants, SpARK-P and SpARK-R, which achieve sparsity by anchoring watermarked tokens to words that have specific Part-of-Speech (POS) tags and specific hash values w.r.t a pseudorandom hash function, respectively. Our experimental results demonstrate that the proposed watermarking schemes, albeit embarrassingly simple, are incredibly effective, achieving high detectability while generating text that outperforms previous LLM watermarking methods in quality across various tasks. SpARK further advances the watermarking capability for LLMs while maintaining their generated text quality.
%U https://aclanthology.org/2026.findings-eacl.240/
%P 4603-4626
Markdown (Informal)
[SpARK: An Embarrassingly Simple Sparse Watermarking in LLMs with Enhanced Text Quality](https://aclanthology.org/2026.findings-eacl.240/) (Hoang et al., Findings 2026)
ACL