LLMs are Imperfect, Then What? An Empirical Study on LLM Failures in Software Engineering
Jiessie Tie, Bingsheng Yao, Tianshi Li, Syed Ishtiaque Ahmed, Dakuo Wang, Shurui Zhou
TL;DR
The cases where ChatGPT failed, their root causes, and the corresponding mitigation solutions used by users are identified to contribute to the overall understanding and strategies for human-AI interaction on SE tasks.
Abstract
Software engineers are integrating AI assistants into their workflows to enhance productivity and reduce cognitive strain. However, experiences vary significantly, with some engineers finding large language models (LLMs), like ChatGPT, beneficial, while others consider them counterproductive. Researchers also found that ChatGPT's answers included incorrect information. Given the fact that LLMs are still imperfect, it is important to understand how to best incorporate LLMs into the workflow for software engineering (SE) task completion. Therefore, we conducted an observational study with 22 participants using ChatGPT as a coding assistant in a non-trivial SE task to understand the practices, challenges, and opportunities for using LLMs for SE tasks. We identified the cases where ChatGPT failed, their root causes, and the corresponding mitigation solutions used by users. These findings contribute to the overall understanding and strategies for human-AI interaction on SE tasks. Our study also highlights future research and tooling support directions.