Reflecting on Empirical and Sustainability Aspects of Software Engineering Research in the Era of Large Language Models
By: David Williams , Max Hort , Maria Kechagia and more
Potential Business Impact:
Improves how we test and use AI in computer programs.
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.
Similar Papers
Guidelines for Empirical Studies in Software Engineering involving Large Language Models
Software Engineering
Makes computer studies easier to check and repeat.
Guidelines for Empirical Studies in Software Engineering involving Large Language Models
Software Engineering
Makes computer studies easier to check and repeat.
Large Language Models for Software Engineering: A Reproducibility Crisis
Software Engineering
Makes science experiments with AI easier to repeat.