Document Type
Article
Publication Date
2026
Abstract
Generative AI is set to transform the legal profession, though its most promising uses and ultimate effects are still unclear. While AI models like GPT-4 improve efficiency, they can also “hallucinate” and may undermine legal judgment, particularly in complex tasks typically handled by skilled lawyers. This article examines two emerging AI innovations that may mitigate these concerns: Retrieval Augmented Generation (RAG), which grounds AI-powered analysis in legal sources, and AI reasoning models, which structure complex reasoning before generating output. We conduct the first randomized controlled trial assessing these technologies, assigning upper-level law students to complete legal tasks using a RAG-powered legal AI tool (Vincent AI, 2024), an AI reasoning model (OpenAI’s o1-preview), or no AI. We find that both AI tools significantly enhance legal work quality, a marked contrast with previous research examining older large language models like GPT-4. Moreover, these newer models appear to maintain the efficiency benefits associated with older AI technologies. Our findings also show that these AI tools significantly boost productivity in five out of six tested legal tasks, with statistically significant gains of anywhere from 50% to 130%. They perform exceptionally well in complex tasks like drafting persuasive letters and analyzing complaints. Notably, o1- preview improves the analytical depth of work product and Vincent AI avoids introducing more hallucinations, suggesting that integrating domain-specific RAG capabilities with reasoning models could yield even larger improvements.
Recommended Citation
Schwarcz, Daniel, Sam Manning, Patrick Barry, David R. Cleveland, J.J. Prescott, Beverly Rich. "AI-Powered Lawyering: AI Reasoning Models, Retrieval Augmented Generation, and the Future of Legal Practice." Journal of Law and Empirical Analysis, 2026. DOI: https://doi.org/10.1177/2755323X261427048
Appendix: AI-Powered Lawyering
sj-pdf-2-lex-10.1177_2755323x261427048.pdf (310 kB)
Appendix 2
Included in
Artificial Intelligence and Robotics Commons, Legal Education Commons, Legal Profession Commons
Comments
This article is available under the Creative Commons CC-BY-NC license and permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited.
Ethics Approval
The IRB at both the University of Minnesota and University of Michigan reviewed the study design and determined that it met the criteria for exemption from IRB review.
Funder Statement
Fredrikson & Byron PA, Robins Kaplan LLC, University of Minnesota Law School, and University of Michigan Law School all provided generous financial support for this project. Neither OpenAI nor VLex (the company that owns Vincent AI) provided financial support for this project, but they both did make their AI platforms freely available to study participants.