Empirical and Sustainability Aspects of Software Engineering Research in the Era of Large Language Models: A Reflection

TL;DR

This paper reviews the current state of software engineering research involving large language models, focusing on challenges like benchmarking, replicability, contamination, and sustainability, and offers recommendations for improvement.

Contribution

It provides a structured overview of LLM-based SE research, highlighting practices, shortcomings, and proposing strategies to enhance rigour and sustainability.

Findings

Highlights encouraging practices in LLM-based SE research

Identifies persistent shortcomings in benchmarking and replicability

Recommends strategies to improve sustainability and rigour

Abstract

Software Engineering (SE) research involving the use of Large Language Models (LLMs) has introduced several new challenges related to rigour in benchmarking, contamination, replicability, and sustainability. In this paper, we invite the research community to reflect on how these challenges are addressed in SE. Our results provide a structured overview of current LLM-based SE research at ICSE, highlighting both encouraging practices and persistent shortcomings. We conclude with recommendations to strengthen benchmarking rigour, improve replicability, and address the financial and environmental costs of LLM-based SE.