@inproceedings{emi-etal-2025-pangram,
title = "Pangram at {G}en{AI} Detection Task 3: An Active Learning Approach to Machine-Generated Text Detection",
author = "Emi, Bradley N. and
Spero, Max and
Masrour, Elyas",
editor = "Alam, Firoj and
Nakov, Preslav and
Habash, Nizar and
Gurevych, Iryna and
Chowdhury, Shammur and
Shelmanov, Artem and
Wang, Yuxia and
Artemova, Ekaterina and
Kutlu, Mucahid and
Mikros, George",
booktitle = "Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "International Conference on Computational Linguistics",
url = "https://aclanthology.org/2025.genaidetect-1.40/",
pages = "347--351",
abstract = "We pretrain an autoregressive LLM-based detector on a wide variety of datasets, domains, languages, prompt schemes, and LLMs used to generate the AI portion of the dataset. We aggressively employ several augmentation strategies and preprocessing strategies to improve robustness. We then mine the RAID train set for the AI examples with the largest error based on the original classifier, and mix those examples and their human-written counterparts back into the training set. We then retrain the detector until convergence."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="emi-etal-2025-pangram">
<titleInfo>
<title>Pangram at GenAI Detection Task 3: An Active Learning Approach to Machine-Generated Text Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bradley</namePart>
<namePart type="given">N</namePart>
<namePart type="family">Emi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Max</namePart>
<namePart type="family">Spero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elyas</namePart>
<namePart type="family">Masrour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Shelmanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxia</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Artemova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mucahid</namePart>
<namePart type="family">Kutlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Mikros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Conference on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We pretrain an autoregressive LLM-based detector on a wide variety of datasets, domains, languages, prompt schemes, and LLMs used to generate the AI portion of the dataset. We aggressively employ several augmentation strategies and preprocessing strategies to improve robustness. We then mine the RAID train set for the AI examples with the largest error based on the original classifier, and mix those examples and their human-written counterparts back into the training set. We then retrain the detector until convergence.</abstract>
<identifier type="citekey">emi-etal-2025-pangram</identifier>
<location>
<url>https://aclanthology.org/2025.genaidetect-1.40/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>347</start>
<end>351</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pangram at GenAI Detection Task 3: An Active Learning Approach to Machine-Generated Text Detection
%A Emi, Bradley N.
%A Spero, Max
%A Masrour, Elyas
%Y Alam, Firoj
%Y Nakov, Preslav
%Y Habash, Nizar
%Y Gurevych, Iryna
%Y Chowdhury, Shammur
%Y Shelmanov, Artem
%Y Wang, Yuxia
%Y Artemova, Ekaterina
%Y Kutlu, Mucahid
%Y Mikros, George
%S Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)
%D 2025
%8 January
%I International Conference on Computational Linguistics
%C Abu Dhabi, UAE
%F emi-etal-2025-pangram
%X We pretrain an autoregressive LLM-based detector on a wide variety of datasets, domains, languages, prompt schemes, and LLMs used to generate the AI portion of the dataset. We aggressively employ several augmentation strategies and preprocessing strategies to improve robustness. We then mine the RAID train set for the AI examples with the largest error based on the original classifier, and mix those examples and their human-written counterparts back into the training set. We then retrain the detector until convergence.
%U https://aclanthology.org/2025.genaidetect-1.40/
%P 347-351
Markdown (Informal)
[Pangram at GenAI Detection Task 3: An Active Learning Approach to Machine-Generated Text Detection](https://aclanthology.org/2025.genaidetect-1.40/) (Emi et al., GenAIDetect 2025)
ACL