Empirical and Sustainability Aspects of Software Engineering Research in the Era of Large Language Models: A Reflection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914262445719552 |
|---|---|
| author | Williams, David Hort, Max Kechagia, Maria Aleti, Aldeida Petke, Justyna Sarro, Federica |
| author_facet | Williams, David Hort, Max Kechagia, Maria Aleti, Aldeida Petke, Justyna Sarro, Federica |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_26538 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Empirical and Sustainability Aspects of Software Engineering Research in the Era of Large Language Models: A Reflection Williams, David Hort, Max Kechagia, Maria Aleti, Aldeida Petke, Justyna Sarro, Federica Software Engineering 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. |
| title | Empirical and Sustainability Aspects of Software Engineering Research in the Era of Large Language Models: A Reflection |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2510.26538 |