Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Journal articles
  4. Challenges to Using Large Language Models in Code Generation and Repair
 
research article

Challenges to Using Large Language Models in Code Generation and Repair

Pasquale, Liliana
•
Sabetta, Antonino
•
d’Amorim, Marcelo
Show more
March 2025
IEEE Security & Privacy

Large language models (LLMs) hold great promise in solving many challenges arising from software complexity, including the possibility of automating code generation and repair. Although we cannot deny the groundbreaking nature of LLM-based code repair, we must be realistic in positioning current results.

  • Details
  • Metrics
Type
research article
DOI
10.1109/msec.2025.3530488
Author(s)
Pasquale, Liliana

University College Dublin, Dublin, Ireland

Sabetta, Antonino

SAP, Mougins, France

d’Amorim, Marcelo

North Carolina State University, Raleigh, NC, USA

Hegedűs, Péter

Department of Software Engineering, University of Szeged, Szeged, Hungary

Mirakhorli, Mehdi Tarrit

University of Hawaii at Manoa, Honolulu, HI, USA

Okhravi, Hamed

Massachusetts Institute of Technology (MIT) Lincoln Laboratory, Lexington, MA, USA

Payer, Mathias  

École Polytechnique Fédérale de Lausanne

Rashid, Awais

University of Bristol, Bristol, U.K.

Santos, Joanna C. S.

Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, USA

Spring, Jonathan M.

Cybersecurity and Infrastructure Security Agency, VA, USA

Show more
Date Issued

2025-03

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Published in
IEEE Security & Privacy
Volume

23

Issue

2

Start page

81

End page

88

Editorial or Peer reviewed

REVIEWED

Written at

EPFL

EPFL units
HEXHIVE  
Available on Infoscience
April 14, 2025
Use this identifier to reference this record
https://infoscience.epfl.ch/handle/20.500.14299/249155
Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés