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

TL;DR

This paper investigates the challenges faced by developers when integrating Large Language Models into software products and explores emerging solutions through interviews and surveys, providing insights for improving LLM-based development.

Contribution

It identifies 19 emerging solutions for quality assurance in LLM integration, based on mixed-method research with industry practitioners, highlighting practical approaches to overcome challenges.

Findings

Identified 19 emerging solutions for LLM integration challenges.

Provided insights from 26 interviews and 332 survey responses.

Guided future development and evaluation of LLM-based products.

Abstract

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.