@inproceedings{gritsai-etal-2024-multi,
title = "Multi-head Span-based Detector for {AI}-generated Fragments in Scientific Papers",
author = "Gritsai, German and
Khabutdinov, Ildar and
Grabovoy, Andrey",
editor = "Ghosal, Tirthankar and
Singh, Amanpreet and
Waard, Anita and
Mayr, Philipp and
Naik, Aakanksha and
Weller, Orion and
Lee, Yoonjoo and
Shen, Shannon and
Qin, Yanxia",
booktitle = "Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.sdp-1.21",
pages = "220--225",
abstract = "This paper describes a system designed to distinguish between AI-generated and human-written scientific excerpts in the DAGPap24 competition hosted within the Fourth Workshop on Scientific Document Processing. In this competition the task is to find artificially generated token-level text fragments in documents of a scientific domain. Our work focuses on the use of a multi-task learning architecture with two heads. The application of this approach is justified by the specificity of the task, where class spans are continuous over several hundred characters. We considered different encoder variations to obtain a state vector for each token in the sequence, as well as a variation in splitting fragments into tokens to further feed into the input of a transform-based encoder. This approach allows us to achieve a 9{\%} quality improvement relative to the baseline solution score on the development set (from 0.86 to 0.95) using the average macro $F_{1}$-score, as well as a score of 0.96 on a closed test part of the dataset from the competition.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gritsai-etal-2024-multi">
<titleInfo>
<title>Multi-head Span-based Detector for AI-generated Fragments in Scientific Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="family">Gritsai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ildar</namePart>
<namePart type="family">Khabutdinov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrey</namePart>
<namePart type="family">Grabovoy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Ghosal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanpreet</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anita</namePart>
<namePart type="family">Waard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Mayr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aakanksha</namePart>
<namePart type="family">Naik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orion</namePart>
<namePart type="family">Weller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoonjoo</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shannon</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanxia</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes a system designed to distinguish between AI-generated and human-written scientific excerpts in the DAGPap24 competition hosted within the Fourth Workshop on Scientific Document Processing. In this competition the task is to find artificially generated token-level text fragments in documents of a scientific domain. Our work focuses on the use of a multi-task learning architecture with two heads. The application of this approach is justified by the specificity of the task, where class spans are continuous over several hundred characters. We considered different encoder variations to obtain a state vector for each token in the sequence, as well as a variation in splitting fragments into tokens to further feed into the input of a transform-based encoder. This approach allows us to achieve a 9% quality improvement relative to the baseline solution score on the development set (from 0.86 to 0.95) using the average macro F₁-score, as well as a score of 0.96 on a closed test part of the dataset from the competition.</abstract>
<identifier type="citekey">gritsai-etal-2024-multi</identifier>
<location>
<url>https://aclanthology.org/2024.sdp-1.21</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>220</start>
<end>225</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-head Span-based Detector for AI-generated Fragments in Scientific Papers
%A Gritsai, German
%A Khabutdinov, Ildar
%A Grabovoy, Andrey
%Y Ghosal, Tirthankar
%Y Singh, Amanpreet
%Y Waard, Anita
%Y Mayr, Philipp
%Y Naik, Aakanksha
%Y Weller, Orion
%Y Lee, Yoonjoo
%Y Shen, Shannon
%Y Qin, Yanxia
%S Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F gritsai-etal-2024-multi
%X This paper describes a system designed to distinguish between AI-generated and human-written scientific excerpts in the DAGPap24 competition hosted within the Fourth Workshop on Scientific Document Processing. In this competition the task is to find artificially generated token-level text fragments in documents of a scientific domain. Our work focuses on the use of a multi-task learning architecture with two heads. The application of this approach is justified by the specificity of the task, where class spans are continuous over several hundred characters. We considered different encoder variations to obtain a state vector for each token in the sequence, as well as a variation in splitting fragments into tokens to further feed into the input of a transform-based encoder. This approach allows us to achieve a 9% quality improvement relative to the baseline solution score on the development set (from 0.86 to 0.95) using the average macro F₁-score, as well as a score of 0.96 on a closed test part of the dataset from the competition.
%U https://aclanthology.org/2024.sdp-1.21
%P 220-225
Markdown (Informal)
[Multi-head Span-based Detector for AI-generated Fragments in Scientific Papers](https://aclanthology.org/2024.sdp-1.21) (Gritsai et al., sdp-WS 2024)
ACL