Uncovering Pretraining Code in LLMs: A Syntax-Aware Attribution Approach
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (1) · 721-729
DOI: 10.1609/aaai.v40i1.37038 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yuanheng Li und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
As large language models (LLMs) become increasingly capable, concerns over the unauthorized use of copyrighted and licensed content in their training data have grown, especially in the context of code. Open-source code, often protected by open source licenses (e.g, GPL), poses legal and ethical challenges when used in pretraining. Detecting whether specific code samples were included in LLM training data is thus critical for transparency, accountability, and copyright compliance. We propose SynPrune, a syntax-pruned membership inference attack method tailored for code. Unlike prior MIA approaches that treat code as plain text, SynPrune leverages the structured and rule-governed nature of programming languages. Specifically, it identifies and excludes consequent tokens that are syntactically required and not reflective of authorship, from attribution when computing membership scores. Experimental results show that SynPrune consistently outperforms the state-of-the-arts. Our method is also robust across varying function lengths and syntax categories.
Zitieren
APA
Li, Y., Chen, Z., Liu, X., Wang, Y., Liu, M., Shi, Y., Huang, K., & Zhao, S. (2026). Uncovering Pretraining Code in LLMs: A Syntax-Aware Attribution Approach. Proceedings of the AAAI Conference on Artificial Intelligence, 40(1), 721-729. https://doi.org/10.1609/aaai.v40i1.37038
Vancouver
Li Y, Chen Z, Liu X, Wang Y, Liu M, Shi Y, et al. Uncovering Pretraining Code in LLMs: A Syntax-Aware Attribution Approach. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(1):721-729. doi:10.1609/aaai.v40i1.37038
BibTeX
@article{Li2026,
author = {Li, Yuanheng and Chen, Zhuoyang and Liu, Xiaoyun and Wang, Yuhao and Liu, Mingwei and Shi, Yang and Huang, Kaifeng and Zhao, Shengjie},
title = {Uncovering Pretraining Code in LLMs: A Syntax-Aware Attribution Approach},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {1},
pages = {721--729},
doi = {10.1609/aaai.v40i1.37038}
}
EUVIMED