@inproceedings{deng-etal-2026-detecting,
title = "Detecting Post-generation Edits to Watermarked {LLM} Outputs via Error-Correcting Codes",
author = "Deng, Zewei and
Siddeek, Muhammad and
Xie, Liyan and
Mohamed, Mohamed and
Wang, Mengdi and
Poor, H. Vincent and
Goldsmith, Andrea",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2142/",
pages = "45788--45796",
ISBN = "979-8-89176-462-0",
abstract = "Watermarking has become a key mechanism for distinguishing AI-generated from human-written texts. In practical settings, however, content produced by large language models (LLMs) is often subject to critical post-generation edits, posing challenges for detecting and localizing such modifications. In this work, we propose incorporating error-correcting codes, specifically Varshamov-Tenengolts (VT) codes, by embedding VT code strings into watermarked LLM outputs, thus enabling post-generation edit detection of token insertions and deletions. We accompany such a watermarking procedure with a watermark detector and a post-edit detector. We evaluate our method on open-source LLM using synthetic edits and demonstrate excellent empirical performance of post-generation edit detection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deng-etal-2026-detecting">
<titleInfo>
<title>Detecting Post-generation Edits to Watermarked LLM Outputs via Error-Correcting Codes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zewei</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Siddeek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liyan</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengdi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">H</namePart>
<namePart type="given">Vincent</namePart>
<namePart type="family">Poor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Goldsmith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Watermarking has become a key mechanism for distinguishing AI-generated from human-written texts. In practical settings, however, content produced by large language models (LLMs) is often subject to critical post-generation edits, posing challenges for detecting and localizing such modifications. In this work, we propose incorporating error-correcting codes, specifically Varshamov-Tenengolts (VT) codes, by embedding VT code strings into watermarked LLM outputs, thus enabling post-generation edit detection of token insertions and deletions. We accompany such a watermarking procedure with a watermark detector and a post-edit detector. We evaluate our method on open-source LLM using synthetic edits and demonstrate excellent empirical performance of post-generation edit detection.</abstract>
<identifier type="citekey">deng-etal-2026-detecting</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2142/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>45788</start>
<end>45796</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Detecting Post-generation Edits to Watermarked LLM Outputs via Error-Correcting Codes
%A Deng, Zewei
%A Siddeek, Muhammad
%A Xie, Liyan
%A Mohamed, Mohamed
%A Wang, Mengdi
%A Poor, H. Vincent
%A Goldsmith, Andrea
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F deng-etal-2026-detecting
%X Watermarking has become a key mechanism for distinguishing AI-generated from human-written texts. In practical settings, however, content produced by large language models (LLMs) is often subject to critical post-generation edits, posing challenges for detecting and localizing such modifications. In this work, we propose incorporating error-correcting codes, specifically Varshamov-Tenengolts (VT) codes, by embedding VT code strings into watermarked LLM outputs, thus enabling post-generation edit detection of token insertions and deletions. We accompany such a watermarking procedure with a watermark detector and a post-edit detector. We evaluate our method on open-source LLM using synthetic edits and demonstrate excellent empirical performance of post-generation edit detection.
%U https://aclanthology.org/2026.findings-emnlp.2142/
%P 45788-45796
Markdown (Informal)
[Detecting Post-generation Edits to Watermarked LLM Outputs via Error-Correcting Codes](https://aclanthology.org/2026.findings-emnlp.2142/) (Deng et al., Findings 2026)
ACL