Large Language Models for Software Engineering: Survey and Open Problems

TL;DR

This survey explores the use of Large Language Models in Software Engineering, highlighting their applications, challenges like hallucinations, and the importance of hybrid approaches for reliable deployment.

Contribution

It provides a comprehensive overview of LLM applications in SE and identifies open research challenges and the potential of hybrid techniques.

Findings

LLMs are applied across all SE activities including coding and documentation.

Emergent properties of LLMs introduce both opportunities and technical challenges.

Hybrid techniques combining traditional SE methods with LLMs are crucial for reliability.

Abstract

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.