EUVIMEDEUVIMED entdecken
Crossref

System L: Toward System 2-Style Legal Reasoning

Chuanyi Li, Yi Feng, Vincent Ng

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (46) · 39728-39736

DOI: 10.1609/aaai.v40i46.41328 ↗

Kurz gefasst

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

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dual-system theory distinguishes between fast, intuitive System 1 and slow, deliberative System 2. While this dichotomy describes many forms of reasoning, it oversimplifies the reality of expert legal reasoning. Legal reasoning is not merely a process of slow, logical deliberation. It is intrinsically normative, embedding precedent analysis, statutory interpretation, policy balancing, and social values. This paper envisions a reasoning architecture for legal reasoning, System L (Legal System 2), which extends traditional System 2 by integrating domain-specific normative frameworks in a structured manner. Using the IRAC (Issue–Rule–Application–Conclusion) structure as a backbone model, System L represents a blueprint for the next generation of cognitive and AI systems capable of human-like legal reasoning.

Zitieren

APA

Li, C., Feng, Y., & Ng, V. (2026). System L: Toward System 2-Style Legal Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(46), 39728-39736. https://doi.org/10.1609/aaai.v40i46.41328

Vancouver

Li C, Feng Y, Ng V. System L: Toward System 2-Style Legal Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(46):39728-39736. doi:10.1609/aaai.v40i46.41328

BibTeX
@article{Li2026,
  author = {Li, Chuanyi and Feng, Yi and Ng, Vincent},
  title = {System L: Toward System 2-Style Legal Reasoning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {46},
  pages = {39728--39736},
  doi = {10.1609/aaai.v40i46.41328}
}
Kostenlos starten →