Legal Rule Induction: Towards Generalizable Principle Discovery from Analogous Judicial Precedents
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909617433346048 |
|---|---|
| author | Fan, Wei Zheng, Tianshi Hu, Yiran Deng, Zheye Wang, Weiqi Xu, Baixuan Li, Chunyang Li, Haoran Shen, Weixing Song, Yangqiu |
| author_facet | Fan, Wei Zheng, Tianshi Hu, Yiran Deng, Zheye Wang, Weiqi Xu, Baixuan Li, Chunyang Li, Haoran Shen, Weixing Song, Yangqiu |
| contents | Legal rules encompass not only codified statutes but also implicit adjudicatory principles derived from precedents that contain discretionary norms, social morality, and policy. While computational legal research has advanced in applying established rules to cases, inducing legal rules from judicial decisions remains understudied, constrained by limitations in model inference efficacy and symbolic reasoning capability. The advent of Large Language Models (LLMs) offers unprecedented opportunities for automating the extraction of such latent principles, yet progress is stymied by the absence of formal task definitions, benchmark datasets, and methodologies. To address this gap, we formalize Legal Rule Induction (LRI) as the task of deriving concise, generalizable doctrinal rules from sets of analogous precedents, distilling their shared preconditions, normative behaviors, and legal consequences. We introduce the first LRI benchmark, comprising 5,121 case sets (38,088 Chinese cases in total) for model tuning and 216 expert-annotated gold test sets. Experimental results reveal that: 1) State-of-the-art LLMs struggle with over-generalization and hallucination; 2) Training on our dataset markedly enhances LLMs capabilities in capturing nuanced rule patterns across similar cases. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_14104 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Legal Rule Induction: Towards Generalizable Principle Discovery from Analogous Judicial Precedents Fan, Wei Zheng, Tianshi Hu, Yiran Deng, Zheye Wang, Weiqi Xu, Baixuan Li, Chunyang Li, Haoran Shen, Weixing Song, Yangqiu Computation and Language Legal rules encompass not only codified statutes but also implicit adjudicatory principles derived from precedents that contain discretionary norms, social morality, and policy. While computational legal research has advanced in applying established rules to cases, inducing legal rules from judicial decisions remains understudied, constrained by limitations in model inference efficacy and symbolic reasoning capability. The advent of Large Language Models (LLMs) offers unprecedented opportunities for automating the extraction of such latent principles, yet progress is stymied by the absence of formal task definitions, benchmark datasets, and methodologies. To address this gap, we formalize Legal Rule Induction (LRI) as the task of deriving concise, generalizable doctrinal rules from sets of analogous precedents, distilling their shared preconditions, normative behaviors, and legal consequences. We introduce the first LRI benchmark, comprising 5,121 case sets (38,088 Chinese cases in total) for model tuning and 216 expert-annotated gold test sets. Experimental results reveal that: 1) State-of-the-art LLMs struggle with over-generalization and hallucination; 2) Training on our dataset markedly enhances LLMs capabilities in capturing nuanced rule patterns across similar cases. |
| title | Legal Rule Induction: Towards Generalizable Principle Discovery from Analogous Judicial Precedents |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2505.14104 |