Saved in:
Bibliographic Details
Main Authors: Tie, Jiessie, Yao, Bingsheng, Li, Tianshi, Fang, Hongbo, Ahmed, Syed Ishtiaque, Wang, Dakuo, Zhou, Shurui
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.09916
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914470217908224
author Tie, Jiessie
Yao, Bingsheng
Li, Tianshi
Fang, Hongbo
Ahmed, Syed Ishtiaque
Wang, Dakuo
Zhou, Shurui
author_facet Tie, Jiessie
Yao, Bingsheng
Li, Tianshi
Fang, Hongbo
Ahmed, Syed Ishtiaque
Wang, Dakuo
Zhou, Shurui
contents Software engineers are increasingly incorporating AI assistants into their workflows to enhance productivity and alleviate cognitive load. However, experiences with large language models (LLMs) such as ChatGPT vary widely. While some engineers find them useful, others deem them counterproductive due to inaccuracies in their responses. Researchers have also observed that ChatGPT often provides incorrect information. Given these limitations, it is crucial to determine how to effectively integrate LLMs into software engineering (SE) workflow. Analyzing data from 26 participants in a complex web development task, we identified nine failure types categorized into incorrect or incomplete responses, cognitive overload, and context loss. Users attempted to mitigate these issues through scaffolding, prompt clarification, and debugging. However, 17 participants ultimately chose to abandon ChatGPT due to persistent failures. Our quantitative analysis revealed that unhelpful responses increased the likelihood of abandonment by a factor of 11, while each additional prompt reduced abandonment probability by 17%. This study advances the understanding of human-AI interaction in SE tasks and outlines directions for future research and tooling support.
format Preprint
id arxiv_https___arxiv_org_abs_2411_09916
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle "Should I Give Up Now?" Investigating LLM Pitfalls in Software Engineering
Tie, Jiessie
Yao, Bingsheng
Li, Tianshi
Fang, Hongbo
Ahmed, Syed Ishtiaque
Wang, Dakuo
Zhou, Shurui
Software Engineering
Software engineers are increasingly incorporating AI assistants into their workflows to enhance productivity and alleviate cognitive load. However, experiences with large language models (LLMs) such as ChatGPT vary widely. While some engineers find them useful, others deem them counterproductive due to inaccuracies in their responses. Researchers have also observed that ChatGPT often provides incorrect information. Given these limitations, it is crucial to determine how to effectively integrate LLMs into software engineering (SE) workflow. Analyzing data from 26 participants in a complex web development task, we identified nine failure types categorized into incorrect or incomplete responses, cognitive overload, and context loss. Users attempted to mitigate these issues through scaffolding, prompt clarification, and debugging. However, 17 participants ultimately chose to abandon ChatGPT due to persistent failures. Our quantitative analysis revealed that unhelpful responses increased the likelihood of abandonment by a factor of 11, while each additional prompt reduced abandonment probability by 17%. This study advances the understanding of human-AI interaction in SE tasks and outlines directions for future research and tooling support.
title "Should I Give Up Now?" Investigating LLM Pitfalls in Software Engineering
topic Software Engineering
url https://arxiv.org/abs/2411.09916