EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Don’t Use a Cannon to Kill a Fly: Lightweight Model Editing for LLMs to Correct Deprecated API Recommendations

Guancheng Lin, Xiao Yu, Jacky Keung, Xing Hu, Xin Xia, Alex X. Liu

Proceedings of the ACM on Software Engineering · 01.10.2026 · 3 (ISSTA) · 896-918

DOI: 10.1145/3832130 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Software Engineering, online erschienen am 01.10.2026. Verfasst von Guancheng Lin und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 77 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Zhejiang Provincial Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • National Natural Science Foundation of China
  • Zhejiang Provincial Natural Science Foundation of China

Zitieren

APA

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

Vancouver

Lin G, Yu X, Keung J, Hu X, Xia X, Liu AX. 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. 2026;3(ISSTA):896-918. doi:10.1145/3832130

BibTeX
@article{Lin2026,
  author = {Lin, Guancheng and Yu, Xiao and Keung, Jacky and Hu, Xing and Xia, Xin and Liu, Alex X.},
  title = {Don’t Use a Cannon to Kill a Fly: Lightweight Model Editing for LLMs to Correct Deprecated API Recommendations},
  journal = {Proceedings of the ACM on Software Engineering},
  year = {2026},
  volume = {3},
  number = {ISSTA},
  pages = {896--918},
  doi = {10.1145/3832130}
}
Kostenlos starten →