Forthcoming Works - Journal Articles & Working Papers
Andrew Blair-Stanek & Benjamin Van Durme, LLMs Provide Unstable Answers to Legal Questions (working paper). [WWW]
Visiting Associate Professor of Law
Andrew Blair-Stanek
A.B., Princeton; J.D., Yale
Andrew Blair-Stanek teaches tax law, finance, and accounting. His research interest is using artificial intelligence to identify tax-minimization strategies before taxpayers use them.
Prior to entering academia, Professor Blair-Stanek practiced tax law at McDermott, Will & Emery, LLP in Washington, DC. He clerked for the Hon. Paul V. Niemeyer, U.S. Court of Appeals for the Fourth Circuit.
Professor Blair-Stanek received his JD from Yale Law School, where he was on the Yale Law Journal and acted in the Yale Law Revue (a comedy troupe). Before attending law school, he worked as a software design engineer for Microsoft Corporation.
Scholarship
Contributions to Law Reviews and Other Scholarly Journals
Andrew Blair-Stanek, Nils Holzenberger & Benjamin Van Durme, Can LLMs Identify Tax Abuse?, 40 Proc. AAAI Conf. on A.I. 38261-38269 (2026).
Book Chapters & Collected Works
Andrew Blair-Stanek & Benjamin Van Durme, LLMs Provide Unstable Answers to Legal Questions, in ICAIL '25: Proceedings of the Twentieth International Conference on Artificial Intelligence and Law 425-429 (New York: Association for Computing Machinery 2026). [WWW]
Ishani Mondal, Michelle Yuan, Anandhavelu N, Aparna Garimella, Francis Ferraro, Andrew Blair-Stanek, Benjamin Van Durme & Jordan Boyd-Graber, ADAPTIVE IE: Investigating the Complementarity of Human-AI Collaboration to Adaptively Extract Information On-the-Fly, in Proceedings of the 31st International Conference on Computational Linguistics 5870-5889 (Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio & Steven Schockaert eds., Stroudsburg, Pa.: Association for Computational Linguistics 2025). [WWW]
Andrew Blair-Stanek, Nils Hozenberger & Benjamin Van Durme, BLT: Can Large Language Models Handle Basic Legal Text?, in Proceedings of the Natural Language Processing Workshop 2024, at 216-232 (Nikolaos Aletras, Ilias Chalkidis, Leslie Barrett, Cฤtฤlina Goanศฤ, Daniel Preoศiuc-Pietro & Gerasimos Spanakis eds., Association for Computational Linguistics 2024). [WWW]