Maqola

Large Language Models for Software Engineering: Survey and Open Problems

Angela FanGenerative AI Team Meta Platforms Inc.,New York,NY,USABeliz GokkayaPyTorch Team Meta Platforms Inc.,Menlo Park,CA,USAMark HarmanInstagram Product Foundation Meta Platforms Inc.,London,UKMitya LyubarskiyDeveloper Infrastructure Meta Platforms Inc.,London,UKShubho SenguptaFAIR Meta Platforms Inc.,Menlo Park,CA,USAShin YooSchool of Computing KAIST,Daejeon,KoreaJie M. ZhangKing's College London,Department of Informatics,London,UK

2023en

ABI

Annotatsiya

This paper provides a survey of the emerging area of Large Language Models (LLMs) for Software Engineering (SE). It also sets out open research challenges for the application of LLMs to technical problems faced by software engineers. LLMs' emergent properties bring novelty and creativity with applications right across the spectrum of Software Engineering activities including coding, design, requirements, repair, refactoring, performance improvement, documentation and analytics. However, these very same emergent properties also pose significant technical challenges; we need techniques that can reliably weed out incorrect solutions, such as hallucinations. Our survey reveals the pivotal role that hybrid techniques (traditional SE plus LLMs) have to play in the development and deployment of reliable, efficient and effective LLM-based SE.

Hali tarjima qilinmagan

Identifikatorlar

DOI: 10.1109/icse-fose59343.2023.00008

Iqtiboslar va manbalar

2 ta iqtibos0 ta foydalanilgan manba

Koʻrsatkichlar — AkademScholar