Beyond the Comfort Zone: Emerging Solutions to Overcome Challenges in Integrating LLMs into Software Products

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Nahar, Nadia, Kästner, Christian, Butler, Jenna, Parnin, Chris, Zimmermann, Thomas, Bird, Christian
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912144783572992
author Nahar, Nadia
Kästner, Christian
Butler, Jenna
Parnin, Chris
Zimmermann, Thomas
Bird, Christian
author_facet Nahar, Nadia
Kästner, Christian
Butler, Jenna
Parnin, Chris
Zimmermann, Thomas
Bird, Christian
contents Large Language Models (LLMs) are increasingly embedded into software products across diverse industries, enhancing user experiences, but at the same time introducing numerous challenges for developers. Unique characteristics of LLMs force developers, who are accustomed to traditional software development and evaluation, out of their comfort zones as the LLM components shatter standard assumptions about software systems. This study explores the emerging solutions that software developers are adopting to navigate the encountered challenges. Leveraging a mixed-method research, including 26 interviews and a survey with 332 responses, the study identifies 19 emerging solutions regarding quality assurance that practitioners across several product teams at Microsoft are exploring. The findings provide valuable insights that can guide the development and evaluation of LLM-based products more broadly in the face of these challenges.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12071
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Beyond the Comfort Zone: Emerging Solutions to Overcome Challenges in Integrating LLMs into Software Products
Nahar, Nadia
Kästner, Christian
Butler, Jenna
Parnin, Chris
Zimmermann, Thomas
Bird, Christian
Software Engineering
Machine Learning
Large Language Models (LLMs) are increasingly embedded into software products across diverse industries, enhancing user experiences, but at the same time introducing numerous challenges for developers. Unique characteristics of LLMs force developers, who are accustomed to traditional software development and evaluation, out of their comfort zones as the LLM components shatter standard assumptions about software systems. This study explores the emerging solutions that software developers are adopting to navigate the encountered challenges. Leveraging a mixed-method research, including 26 interviews and a survey with 332 responses, the study identifies 19 emerging solutions regarding quality assurance that practitioners across several product teams at Microsoft are exploring. The findings provide valuable insights that can guide the development and evaluation of LLM-based products more broadly in the face of these challenges.
title Beyond the Comfort Zone: Emerging Solutions to Overcome Challenges in Integrating LLMs into Software Products
topic Software Engineering
Machine Learning
url https://arxiv.org/abs/2410.12071