LLMs Meet Library Evolution: Evaluating Deprecated API Usage in LLM-Based Code Completion

Large language models (LLMs), pre-trained or fine-tuned on large code corpora, have shown effectiveness in generating code completions. However, in LLM-based code completion, LLMs may struggle to use correct and up-to-date Application Programming Interfaces (APIs) due to the rapid and continuous evo...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings / International Conference on Software Engineering pp. 885 - 897
Main Authors: Wang, Chong, Huang, Kaifeng, Zhang, Jian, Feng, Yebo, Zhang, Lyuye, Liu, Yang, Peng, Xin
Format: Conference Proceeding
Language:English
Published: IEEE 26.04.2025
Subjects:
api deprecation
Application programming interfaces
code completion
Codes
Faces
Large language models
Libraries
library evolution
Python
Software development management
Software engineering
ISSN:1558-1225
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Large language models (LLMs), pre-trained or fine-tuned on large code corpora, have shown effectiveness in generating code completions. However, in LLM-based code completion, LLMs may struggle to use correct and up-to-date Application Programming Interfaces (APIs) due to the rapid and continuous evolution of libraries. While existing studies have highlighted issues with predicting incorrect APIs, the specific problem of deprecated API usage in LLM-based code completion has not been thoroughly investigated. To address this gap, we conducted the first evaluation study on deprecated API usage in LLM-based code completion. This study involved seven advanced LLMs, 145 API mappings from eight popular Python libraries, and \mathbf{2 8, 1 2 5} completion prompts. The study results reveal the status quo (i.e., API usage plausibility and deprecated usage rate) of deprecated API and replacing API usage in LLM-based code completion from the perspectives of model, prompt, and library, and indicate the root causes behind. Based on these findings, we propose two lightweight fixing approaches, Replaceapi and InsertPrompt, which can serve as baseline approaches for future research on mitigating deprecated API usage in LLM-based completion. Additionally, we provide implications for future research on integrating library evolution with LLMdriven software development.
ISSN:1558-1225
DOI:10.1109/ICSE55347.2025.00245