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

TL;DR

This paper evaluates how large language models handle deprecated API usage in code completion, revealing current challenges and proposing baseline solutions to improve API update handling in evolving libraries.

Contribution

It is the first comprehensive evaluation of deprecated API usage in LLM-based code completion and introduces two baseline fixing approaches, REPLACEAPI and INSERTPROMPT.

Findings

High deprecated API usage rate in LLM outputs

Model and prompt influence deprecated API usage

Baseline approaches reduce deprecated API usage

Abstract

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 28,125 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 LLM-driven software development.