Gå til søgefeltetSpring over til navigationSpring til hovedindhold

Get on the Train or be Left on the Station: Using LLMs for Software Engineering Research.

  • Bianca Trinkenreich
    ,
  • Fabio Calefato
    ,
  • Geir Hanssen
    ,
  • Kelly Blincoe
    ,
  • Marcos Kalinowski
    ,
  • Mauro Pezzè
  • Colorado State University
    ,
  • The Interaction, Visualization, Usability & UX group at Dip. di Informatica, Bari University
    ,
  • SINTEF Digital
    ,
  • The University of Auckland
    ,
  • Pontifical Catholic University of Rio de Janerio
    ,
  • Università della Svizzera italiana
Publikation:
Artikel i tidsskrift og konference artikel i tidsskrift
Tidsskriftartikel
Forskning
Peer-review

Open Access

Resume

The adoption of Large Language Models (LLMs) is not only transforming software engineering (SE) practice but is also poised to<br/>fundamentally disrupt how research is conducted in the field. While<br/>perspectives on this transformation range from viewing LLMs as<br/>mere productivity tools to considering them revolutionary forces,<br/>we argue that the SE research community must proactively engage<br/>with and shape the integration of LLMs into research practices, emphasizing human agency in this transformation. As LLMs rapidly<br/>become integral to SE research—both as tools that support investigations and as subjects of study—a human-centric perspective is<br/>essential. Ensuring human oversight and interpretability is necessary for upholding scientific rigor, fostering ethical responsibility,<br/>and driving advancements in the field. Drawing from discussions<br/>at the 2nd Copenhagen Symposium on Human-Centered AI in SE,<br/>this position paper employs McLuhan’s Tetrad of Media Laws to<br/>analyze the impact of LLMs on SE research. Through this theoretical lens, we examine how LLMs enhance research capabilities<br/>through accelerated ideation and automated processes, make some<br/>traditional research practices obsolete, retrieve valuable aspects of<br/>historical research approaches, and risk reversal effects when taken<br/>to extremes. Our analysis reveals opportunities for innovation and<br/>potential pitfalls that require careful consideration. We conclude<br/>with a call to action for the SE research community to proactively<br/>harness the benefits of LLMs while developing frameworks and<br/>guidelines to mitigate their risks, to ensure continued rigor and<br/>impact of research in an AI-augmented future.

Publikation information

Produktionstype

Publikation:
Artikel i tidsskrift og konference artikel i tidsskrift
Tidsskriftartikel
Forskning
Peer-review

Originalsprog

Engelsk

Sider fra-til (Antal sider)

Sider 1503-1507 (4 sider)

Tidsskrift (Bind, Nummer)

CoRR

Publikationsmilepæle

  • Udgivet - 2025

Publikationsstatus

Udgivet - 2025

ISSN

0000-0000

Publikations IDer

  • Scopus: 105013964607

Metrikker

PlumX, åbner i en ny fane

Hentninger
20
Antal citationer
5