A review of the applications and tasks of large language models in the legal field
PeerJ Computer Science · 04.05.2026 · 12 · e3836
DOI: 10.7717/peerj-cs.3836 ↗Kurz gefasst
Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 04.05.2026. Verfasst von Gaojun Peng und 5 weiteren Autor:innen. Die Arbeit nennt 87 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The National Natural Science Foundation of China, The Natural Science Foundation of Inner Mongolia Autonomous Region, The Education Science Research 14th 5-Year Plan Project of Inner Mongolia Autonomous Region.
Abstract (Originalsprache)
The rapid advancement of artificial intelligence has significantly accelerated the development of intelligent judicial systems, bringing profound transformations to both legal practice and legal research. As a major breakthrough in natural language processing, Large Language Models (LLMs) have demonstrated substantial potential in legal text analysis, legal reasoning, and intelligent decision support due to their powerful semantic understanding and generative capabilities. However, the intrinsic characteristics of the legal domain—such as its professional rigor, logical strictness, and normative authority—pose substantial challenges to the deployment of LLMs in real-world legal settings. In particular, issues related to interpretability, knowledge timeliness, reasoning consistency, and hallucination remain critical concerns. This survey provides a structured and systematic review of the applications and task-oriented research of LLMs in the legal domain. We first summarize the architectural characteristics, training paradigms, and technical development paths of representative legal-specific LLMs. We then examine three core judicial tasks—similar case retrieval, judicial examination question answering, and legal judgment prediction—by analyzing commonly used datasets, evaluation metrics, and methodological advancements. Furthermore, we synthesize the major challenges faced by legal LLMs across these tasks, including hallucination phenomena, insufficient reasoning consistency, and limited integration of domain-specific legal knowledge. Finally, we outline future research directions aimed at enhancing reliability, domain adaptability, and practical applicability, thereby providing guidance for subsequent research in legal artificial intelligence.
Förderung
- The National Natural Science Foundation of China
- The Natural Science Foundation of Inner Mongolia Autonomous Region
- The Education Science Research 14th 5-Year Plan Project of Inner Mongolia Autonomous Region
Zitieren
APA
Peng, G., Li, D., Wang, G., Guo, S., Su, L., & Yu, T. (2026). A review of the applications and tasks of large language models in the legal field. PeerJ Computer Science, 12, e3836. https://doi.org/10.7717/peerj-cs.3836
Vancouver
Peng G, Li D, Wang G, Guo S, Su L, Yu T. A review of the applications and tasks of large language models in the legal field. PeerJ Computer Science. 2026;12:e3836. doi:10.7717/peerj-cs.3836
BibTeX
@article{Peng2026,
author = {Peng, Gaojun and Li, Dapeng and Wang, Gang and Guo, Shuang and Su, Lina and Yu, Tianxue},
title = {A review of the applications and tasks of large language models in the legal field},
journal = {PeerJ Computer Science},
year = {2026},
volume = {12},
pages = {e3836},
doi = {10.7717/peerj-cs.3836}
}
EUVIMED