Journal article · 2026 · Open access
Don’t Use a Cannon to Kill a Fly: Lightweight Model Editing for LLMs to Correct Deprecated API Recommendations
Proceedings of the ACM on software engineering., 3(ISSTA), 896–918 · Published 1 October 2026 · DOI 10.1145/3832130
In brief
“Don’t Use a Cannon to Kill a Fly: Lightweight Model Editing for LLMs to Correct Deprecated API Recommendations” is a 2026 journal article by Guancheng Lin and 5 co-authors, published in Proceedings of the ACM on software engineering.. OpenAlex counts 7 citations as of 19 November 2026, which puts it in the top 2% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Proceedings of the ACM on software engineering..
- Citations
- 7
- Most cited in
- 2026 (7)
- Field-weighted impact
- 18.00
- References
- 76
- Authors
- 6
Abstract
Pre-trained or fine-tuned on large code corpora, Large Language Models (LLMs) have demonstrated strong performance in code completion tasks. However, their embedded knowledge is constrained by the timeliness of training data, which often includes code using deprecated APIs. Consequently, LLMs frequently generate deprecated APIs that will no longer be supported in future versions of third-party libraries. While retraining LLMs on updated codebases could refresh their API knowledge, this approach is computationally expensive. Recently, lightweight model editing methods have emerged to efficiently correct specific knowledge in LLMs. However, it remains unclear whether these methods can effectively update deprecated API knowledge and enable edited models to generate up-to-date APIs. To address this gap, we conduct the first systematic study applying 10 state-of-the-art model editing techniques to update deprecated API knowledge in three LLMs: Qwen2.5-Coder, CodeGemma, and DeepSeek-Coder. We introduce EDAPIBench, a dedicated benchmark featuring over 70 deprecated APIs from 8 popular Python libraries, with more than 3,000 editing instances. Our results show that the parameter-efficient fine-tuning method AdaLoRA achieves the best performance in enabling edited models to generate correct, up-to-date APIs, but falls short in Specificity (i.e., the editing influences untargeted knowledge). To resolve this, we propose AdaLoRA-L, which defines "Common API Layers" (layers within the LLMs with high importance across all APIs, storing general knowledge and excluded from editing) and restricts edits exclusively to "Specific API Layers" (layers with high importance only for the target API, storing the API-specific knowledge). Experimental results demonstrate that AdaLoRA-L significantly improves Specificity while maintaining comparable performance across other evaluation metrics.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Lin, G., Yu, X., Keung, J., Hu, X., Xia, X., & Liu, A. X. (2026). Don’t Use a Cannon to Kill a Fly: Lightweight Model Editing for LLMs to Correct Deprecated API Recommendations. Proceedings of the ACM on software engineering., 3(ISSTA), 896–918. https://doi.org/10.1145/3832130
MLA 9
Lin, Guancheng, et al. “Don’t Use a Cannon to Kill a Fly: Lightweight Model Editing for LLMs to Correct Deprecated API Recommendations.” Proceedings of the ACM on software engineering., vol. 3, no. ISSTA, 2026, pp. 896–918. https://doi.org/10.1145/3832130.
Chicago
Lin, Guancheng, Xiao Yu, Jacky Keung, Xing Hu, Xin Xia, and Alex X. Liu. 2026. “Don’t Use a Cannon to Kill a Fly: Lightweight Model Editing for LLMs to Correct Deprecated API Recommendations.” Proceedings of the ACM on software engineering. 3 (ISSTA): 896–918. https://doi.org/10.1145/3832130.
Harvard
Lin, G. et al. (2026) ‘Don’t Use a Cannon to Kill a Fly: Lightweight Model Editing for LLMs to Correct Deprecated API Recommendations’, Proceedings of the ACM on software engineering., 3(ISSTA), pp. 896–918. doi:10.1145/3832130.
IEEE
G. Lin, X. Yu, J. Keung, X. Hu, X. Xia, and A. X. Liu, “Don’t Use a Cannon to Kill a Fly: Lightweight Model Editing for LLMs to Correct Deprecated API Recommendations,” Proceedings of the ACM on software engineering., vol. 3, no. ISSTA, pp. 896–918, 2026, doi: 10.1145/3832130.
BibTeX
@article{lin2026cannon,
title = {{Don’t Use a Cannon to Kill a Fly: Lightweight Model Editing for LLMs to Correct Deprecated API Recommendations}},
author = {Lin, Guancheng and Yu, Xiao and Keung, Jacky and Hu, Xing and Xia, Xin and Liu, Alex X.},
journal = {Proceedings of the ACM on software engineering.},
year = {2026},
volume = {3},
number = {ISSTA},
pages = {896--918},
doi = {10.1145/3832130},
url = {https://doi.org/10.1145/3832130}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- large language models
- model editing
- API recommendation
- parameter-efficient fine-tuning
- Python library
- code generation
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?
Lin, G., Yu, X., Keung, J., Hu, X., Xia, X., & Liu, A. X. (2026). Don’t Use a Cannon to Kill a Fly: Lightweight Model Editing for LLMs to Correct Deprecated API Recommendations. Proceedings of the ACM on software engineering., 3(ISSTA), 896–918. https://doi.org/10.1145/3832130
How many times has this paper been cited?
7 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 Proceedings of the ACM on software engineering.: sign in and open the PDF from this page.
Who wrote this paper?
Guancheng Lin, Xiao Yu, Jacky Keung, Xing Hu, Xin Xia, Alex X. Liu.
What is the DOI of this paper?
10.1145/3832130, permanently at https://doi.org/10.1145/3832130. 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.