@inproceedings{uchendu-2026-synthetic,
title = "Synthetic Text Detection in the Age of Large Language Models: Watermark vs. Automatic Detection",
author = "Uchendu, Adaku",
editor = "Li, Yunyao and
Rehm, Georg and
Tu, Mei",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-industry.9/",
pages = "113--126",
ISBN = "979-8-89176-394-4",
abstract = "Given the ubiquitous nature of Large Language Models (LLMs) and its impressive capabilities, malicious uses of this technology to generate harmful content have been observed. Thus, to mitigate this serious security risk LLMs pose, many researchers have proposed two techniques for detecting synthetic texts generated from LLMs - watermark and automatic detection. The idea with watermarking LLMs involves infusing generated content with algorithmically-identifiable patterns during generation. This makes accurate synthetic text detection achievable with watermark detection. While, for automatic detection, the focus is on using statistical and linguistic cues to reveal authorship of texts as human or LLM. Currently, both types of synthetic text detectors achieve state-of-the-art performance, however, the better detector is still unknown. To ascertain the better detection method, we evaluate each method on their performance on both unperturbed and perturbed (i.e., adversarially manipulated texts) data. We perform a comprehensive study across six different sizes of Qwen2.5 models, six watermark techniques and detectors, two automatic detectors, three authorship obfuscation methods for different levels of syntactic changes, and two datasets of different text lengths. Our results suggest that there is no detector that consistently outperforms on all scenarios. However, we observe that the (1) automatic detectors are better for short synthetic text detection; and (2) watermark detectors perform better defending against the word-level attack implemented."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="uchendu-2026-synthetic">
<titleInfo>
<title>Synthetic Text Detection in the Age of Large Language Models: Watermark vs. Automatic Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adaku</namePart>
<namePart type="family">Uchendu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-394-4</identifier>
</relatedItem>
<abstract>Given the ubiquitous nature of Large Language Models (LLMs) and its impressive capabilities, malicious uses of this technology to generate harmful content have been observed. Thus, to mitigate this serious security risk LLMs pose, many researchers have proposed two techniques for detecting synthetic texts generated from LLMs - watermark and automatic detection. The idea with watermarking LLMs involves infusing generated content with algorithmically-identifiable patterns during generation. This makes accurate synthetic text detection achievable with watermark detection. While, for automatic detection, the focus is on using statistical and linguistic cues to reveal authorship of texts as human or LLM. Currently, both types of synthetic text detectors achieve state-of-the-art performance, however, the better detector is still unknown. To ascertain the better detection method, we evaluate each method on their performance on both unperturbed and perturbed (i.e., adversarially manipulated texts) data. We perform a comprehensive study across six different sizes of Qwen2.5 models, six watermark techniques and detectors, two automatic detectors, three authorship obfuscation methods for different levels of syntactic changes, and two datasets of different text lengths. Our results suggest that there is no detector that consistently outperforms on all scenarios. However, we observe that the (1) automatic detectors are better for short synthetic text detection; and (2) watermark detectors perform better defending against the word-level attack implemented.</abstract>
<identifier type="citekey">uchendu-2026-synthetic</identifier>
<location>
<url>https://aclanthology.org/2026.acl-industry.9/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>113</start>
<end>126</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Synthetic Text Detection in the Age of Large Language Models: Watermark vs. Automatic Detection
%A Uchendu, Adaku
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F uchendu-2026-synthetic
%X Given the ubiquitous nature of Large Language Models (LLMs) and its impressive capabilities, malicious uses of this technology to generate harmful content have been observed. Thus, to mitigate this serious security risk LLMs pose, many researchers have proposed two techniques for detecting synthetic texts generated from LLMs - watermark and automatic detection. The idea with watermarking LLMs involves infusing generated content with algorithmically-identifiable patterns during generation. This makes accurate synthetic text detection achievable with watermark detection. While, for automatic detection, the focus is on using statistical and linguistic cues to reveal authorship of texts as human or LLM. Currently, both types of synthetic text detectors achieve state-of-the-art performance, however, the better detector is still unknown. To ascertain the better detection method, we evaluate each method on their performance on both unperturbed and perturbed (i.e., adversarially manipulated texts) data. We perform a comprehensive study across six different sizes of Qwen2.5 models, six watermark techniques and detectors, two automatic detectors, three authorship obfuscation methods for different levels of syntactic changes, and two datasets of different text lengths. Our results suggest that there is no detector that consistently outperforms on all scenarios. However, we observe that the (1) automatic detectors are better for short synthetic text detection; and (2) watermark detectors perform better defending against the word-level attack implemented.
%U https://aclanthology.org/2026.acl-industry.9/
%P 113-126
Markdown (Informal)
[Synthetic Text Detection in the Age of Large Language Models: Watermark vs. Automatic Detection](https://aclanthology.org/2026.acl-industry.9/) (Uchendu, ACL 2026)
ACL