EUVIMEDEUVIMED entdecken
Crossref

Can LLMs Identify Tax Abuse?

Andrew Blair-Stanek, Nils Holzenberger, Benjamin Van Durme

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (45) · 38261-38269

DOI: 10.1609/aaai.v40i45.41165 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Andrew Blair-Stanek und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We investigate whether large language models can discover and analyze U.S. tax-minimization strategies. This real-world domain challenges even seasoned human experts, and progress can reduce tax revenue lost from well-advised, wealthy taxpayers. We evaluate the most advanced LLMs on their ability to (1) interpret and verify tax strategies, (2) fill in gaps in partially specified strategies, and (3) generate complete, end-to-end strategies from scratch. This domain should be of particular interest to the LLM reasoning community: unlike synthetic challenge problems or scientific reasoning tasks, U.S. tax law involves navigating hundreds of thousands of pages of statutes, case law, and administrative guidance, all updated regularly. Notably, an LLM identified an apparently novel tax strategy, highlighting these models' potential to revolutionize tax agencies' fight against tax abuse.

Zitieren

APA

Blair-Stanek, A., Holzenberger, N., & Durme, B. V. (2026). Can LLMs Identify Tax Abuse?. Proceedings of the AAAI Conference on Artificial Intelligence, 40(45), 38261-38269. https://doi.org/10.1609/aaai.v40i45.41165

Vancouver

Blair-Stanek A, Holzenberger N, Durme BV. Can LLMs Identify Tax Abuse?. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(45):38261-38269. doi:10.1609/aaai.v40i45.41165

BibTeX
@article{BlairStanek2026,
  author = {Blair-Stanek, Andrew and Holzenberger, Nils and Durme, Benjamin Van},
  title = {Can LLMs Identify Tax Abuse?},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {45},
  pages = {38261--38269},
  doi = {10.1609/aaai.v40i45.41165}
}
Kostenlos starten →