In EDS ansehen

Assessing AI detectors in identifying AI-generated code: Implications for education

Gespeichert in:
Bibliographische Detailangaben
Titel: Assessing AI detectors in identifying AI-generated code: Implications for education
Autoren: PAN, Wei Hung, CHOK, Ming Jie, WONG, Jonathan Leong Shan, SHIN, Yung Xin, POON, Yeong Shian, YANG, Zhou, CHONG, Chun Yong, David LO, LIM, Mei Kuan
Quelle: Research Collection School Of Computing and Information Systems
Verlagsinformationen: Institutional Knowledge at Singapore Management University
Publikationsjahr: 2024
Bestand: Institutional Knowledge (InK) at Singapore Management University
Schlagwörter: Software Engineering Education, AI-Generated Code, AI-Generated Code Detection, Artificial Intelligence and Robotics, Software Engineering
Beschreibung: Educators are increasingly concerned about the usage of Large Language Models (LLMs) such as ChatGPT in programming education, particularly regarding the potential exploitation of imperfections in Artificial Intelligence Generated Content (AIGC) Detectors for academic misconduct.In this paper, we present an empirical study where the LLM is examined for its attempts to bypass detection by AIGC Detectors. This is achieved by generating code in response to a given question using different variants. We collected a dataset comprising 5,069 samples, with each sample consisting of a textual description of a coding problem and its corresponding human-written Python solution codes. These samples were obtained from various sources, including 80 from Quescol, 3,264 from Kaggle, and 1,725 from Leet-Code. From the dataset, we created 13 sets of code problem variant prompts, which were used to instruct ChatGPT to generate the outputs. Subsequently, we assessed the performance of five AIGC detectors. Our results demonstrate that existing AIGC Detectors perform poorly in distinguishing between human-written code and AI-generated code.
Publikationsart: text
Dateibeschreibung: application/pdf
Sprache: English
Relation: https://ink.library.smu.edu.sg/sis_research/9244; https://ink.library.smu.edu.sg/context/sis_research/article/10244/viewcontent/3639474.3640068.pdf
Verfügbarkeit: https://ink.library.smu.edu.sg/sis_research/9244
https://ink.library.smu.edu.sg/context/sis_research/article/10244/viewcontent/3639474.3640068.pdf
Rights: http://creativecommons.org/licenses/by-nc-nd/4.0/
Dokumentencode: edsbas.767B3516
Datenbank: BASE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://ink.library.smu.edu.sg/sis_research/9244#
    Name: EDS - BASE (s4221598)
    Category: fullText
    Text: View record from BASE
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=PAN%20WH
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsbas
DbLabel: BASE
An: edsbas.767B3516
RelevancyScore: 962
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 962.306396484375
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Assessing AI detectors in identifying AI-generated code: Implications for education
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22PAN%2C+Wei+Hung%22">PAN, Wei Hung</searchLink><br /><searchLink fieldCode="AR" term="%22CHOK%2C+Ming+Jie%22">CHOK, Ming Jie</searchLink><br /><searchLink fieldCode="AR" term="%22WONG%2C+Jonathan+Leong+Shan%22">WONG, Jonathan Leong Shan</searchLink><br /><searchLink fieldCode="AR" term="%22SHIN%2C+Yung+Xin%22">SHIN, Yung Xin</searchLink><br /><searchLink fieldCode="AR" term="%22POON%2C+Yeong+Shian%22">POON, Yeong Shian</searchLink><br /><searchLink fieldCode="AR" term="%22YANG%2C+Zhou%22">YANG, Zhou</searchLink><br /><searchLink fieldCode="AR" term="%22CHONG%2C+Chun+Yong%22">CHONG, Chun Yong</searchLink><br /><searchLink fieldCode="AR" term="%22David+LO%22">David LO</searchLink><br /><searchLink fieldCode="AR" term="%22LIM%2C+Mei+Kuan%22">LIM, Mei Kuan</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: Research Collection School Of Computing and Information Systems
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: Institutional Knowledge at Singapore Management University
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2024
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: Institutional Knowledge (InK) at Singapore Management University
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Software+Engineering+Education%22">Software Engineering Education</searchLink><br /><searchLink fieldCode="DE" term="%22AI-Generated+Code%22">AI-Generated Code</searchLink><br /><searchLink fieldCode="DE" term="%22AI-Generated+Code+Detection%22">AI-Generated Code Detection</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+Intelligence+and+Robotics%22">Artificial Intelligence and Robotics</searchLink><br /><searchLink fieldCode="DE" term="%22Software+Engineering%22">Software Engineering</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Educators are increasingly concerned about the usage of Large Language Models (LLMs) such as ChatGPT in programming education, particularly regarding the potential exploitation of imperfections in Artificial Intelligence Generated Content (AIGC) Detectors for academic misconduct.In this paper, we present an empirical study where the LLM is examined for its attempts to bypass detection by AIGC Detectors. This is achieved by generating code in response to a given question using different variants. We collected a dataset comprising 5,069 samples, with each sample consisting of a textual description of a coding problem and its corresponding human-written Python solution codes. These samples were obtained from various sources, including 80 from Quescol, 3,264 from Kaggle, and 1,725 from Leet-Code. From the dataset, we created 13 sets of code problem variant prompts, which were used to instruct ChatGPT to generate the outputs. Subsequently, we assessed the performance of five AIGC detectors. Our results demonstrate that existing AIGC Detectors perform poorly in distinguishing between human-written code and AI-generated code.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: text
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: application/pdf
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: NoteTitleSource
  Label: Relation
  Group: SrcInfo
  Data: https://ink.library.smu.edu.sg/sis_research/9244; https://ink.library.smu.edu.sg/context/sis_research/article/10244/viewcontent/3639474.3640068.pdf
– Name: URL
  Label: Availability
  Group: URL
  Data: https://ink.library.smu.edu.sg/sis_research/9244<br />https://ink.library.smu.edu.sg/context/sis_research/article/10244/viewcontent/3639474.3640068.pdf
– Name: Copyright
  Label: Rights
  Group: Cpyrght
  Data: http://creativecommons.org/licenses/by-nc-nd/4.0/
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsbas.767B3516
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.767B3516
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: Software Engineering Education
        Type: general
      – SubjectFull: AI-Generated Code
        Type: general
      – SubjectFull: AI-Generated Code Detection
        Type: general
      – SubjectFull: Artificial Intelligence and Robotics
        Type: general
      – SubjectFull: Software Engineering
        Type: general
    Titles:
      – TitleFull: Assessing AI detectors in identifying AI-generated code: Implications for education
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: PAN, Wei Hung
      – PersonEntity:
          Name:
            NameFull: CHOK, Ming Jie
      – PersonEntity:
          Name:
            NameFull: WONG, Jonathan Leong Shan
      – PersonEntity:
          Name:
            NameFull: SHIN, Yung Xin
      – PersonEntity:
          Name:
            NameFull: POON, Yeong Shian
      – PersonEntity:
          Name:
            NameFull: YANG, Zhou
      – PersonEntity:
          Name:
            NameFull: CHONG, Chun Yong
      – PersonEntity:
          Name:
            NameFull: David LO
      – PersonEntity:
          Name:
            NameFull: LIM, Mei Kuan
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-locals
              Value: edsbas
            – Type: issn-locals
              Value: edsbas.oa
          Titles:
            – TitleFull: Research Collection School Of Computing and Information Systems
              Type: main
ResultId 1