Conference paper · 2025 · Open access
LLMs Meet Library Evolution: Evaluating Deprecated API Usage in LLM-Based Code Completion
ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion), 885–897 · Published 26 April 2025 · DOI 10.1109/icse55347.2025.00245
In brief
“LLMs Meet Library Evolution: Evaluating Deprecated API Usage in LLM-Based Code Completion” is a 2025 conference paper by Chong Wang and 6 co-authors, published in ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion). OpenAlex counts 81 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 81
- Most cited in
- 2026 (63)
- Field-weighted impact
- 28.88
- References
- 87
- Authors
- 7
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$\mathbf{2 8, 1 2 5}$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.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Wang, C., Huang, K., Zhang, J., Feng, Y., Zhang, L., Liu, Y., & Peng, X. (2025). LLMs Meet Library Evolution: Evaluating Deprecated API Usage in LLM-Based Code Completion. ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion), 885–897. https://doi.org/10.1109/icse55347.2025.00245
MLA 9
Wang, Chong, et al. “LLMs Meet Library Evolution: Evaluating Deprecated API Usage in LLM-Based Code Completion.” ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion), 2025, pp. 885–897. https://doi.org/10.1109/icse55347.2025.00245.
Chicago
Wang, Chong, Kaifeng Huang, Jian Zhang, Yebo Feng, Lyuye Zhang, Yang Liu, and Xin Peng. 2025. “LLMs Meet Library Evolution: Evaluating Deprecated API Usage in LLM-Based Code Completion.” ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion): 885–897. https://doi.org/10.1109/icse55347.2025.00245.
Harvard
Wang, C. et al. (2025) ‘LLMs Meet Library Evolution: Evaluating Deprecated API Usage in LLM-Based Code Completion’, ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion), pp. 885–897. doi:10.1109/icse55347.2025.00245.
IEEE
C. Wang et al., “LLMs Meet Library Evolution: Evaluating Deprecated API Usage in LLM-Based Code Completion,” ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion), pp. 885–897, 2025, doi: 10.1109/icse55347.2025.00245.
BibTeX
@inproceedings{wang2025llms,
title = {{LLMs Meet Library Evolution: Evaluating Deprecated API Usage in LLM-Based Code Completion}},
author = {Wang, Chong and Huang, Kaifeng and Zhang, Jian and Feng, Yebo and Zhang, Lyuye and Liu, Yang and Peng, Xin},
booktitle = {ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)},
year = {2025},
pages = {885--897},
doi = {10.1109/icse55347.2025.00245},
url = {https://doi.org/10.1109/icse55347.2025.00245}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2024 | 1 | |
| 2025 | 17 | |
| 2026 | 63 |
Its field-weighted citation impact is 28.88: it has been cited 28.88 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- library evolution
- API mapping
- Python library
- prompt engineering
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Wang, C., Huang, K., Zhang, J., Feng, Y., Zhang, L., Liu, Y., & Peng, X. (2025). LLMs Meet Library Evolution: Evaluating Deprecated API Usage in LLM-Based Code Completion. ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion), 885–897. https://doi.org/10.1109/icse55347.2025.00245
How many times has this paper been cited?
81 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Chong Wang, Kaifeng Huang, Jian Zhang, Yebo Feng, Lyuye Zhang, Yang Liu, Xin Peng.
What is the DOI of this paper?
10.1109/icse55347.2025.00245, permanently at https://doi.org/10.1109/icse55347.2025.00245. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.