“Should I Give Up Now?” Investigating LLM Pitfalls in 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.

Authors

Institutions

Publication Details

Journal
ACM Transactions on Software Engineering and Methodology
Published
2026-11-18
DOI
https://doi.org/10.1145/3801972
Citations
27
Primary Topic
Software Engineering Research
Type
article
Field-Weighted Citation Impact
48.45

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

“Should I Give Up Now?” Investigating LLM Pitfalls in Software Engineering

Bingsheng Yao, Shurui Zhou, Jiessie Tie, Dakuo Wang et al.
27 citations
ACM Transactions on Software Engineering and Methodology
Software Engineering Research
48.45
article

“Should I Give Up Now?” Investigating LLM Pitfalls in Software Engineering

Bingsheng Yao, Shurui Zhou, Jiessie Tie, Dakuo Wang, Syed Ishtiaque Ahmed, Hongbo Fang
article en
27 citations

Abstract

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.

ACM Transactions on Software Engineering and MethodologyVol. 35(12)
Northeastern University (US), University of Toronto (CA), University of Chicago (US)
School of Cities, University of Toronto, Natural Sciences and Engineering Research Council of Canada
Openalex Percentile: Top 0%
Software Engineering Research
48.45
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon