# Legal Rule Induction: Towards Generalizable Principle Discovery from Analogous Judicial Precedents

arXiv: https://arxiv.org/abs/2505.14104 · HTML: https://mlsanity.com/paper/2505.14104/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 69 references that are in the map.
- First posted on arXiv 20 May 2025.

## Builds on (most cited first, 16 of 16)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models](https://mlsanity.com/paper/2308.11462/) (2023)
- [Neural Legal Judgment Prediction in English](https://mlsanity.com/paper/1906.02059/) (2019)
- [Large Language Models as General Pattern Machines](https://mlsanity.com/paper/2307.04721/) (2023)
- [CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction](https://mlsanity.com/paper/1807.02478/) (2018)
- [Can GPT-3 Perform Statutory Reasoning?](https://mlsanity.com/paper/2302.06100/) (2023)
- [Large Language Models Are Not Strong Abstract Reasoners](https://mlsanity.com/paper/2305.19555/) (2023)
- [A Survey on Legal Judgment Prediction: Datasets, Metrics, Models and Challenges](https://mlsanity.com/paper/2204.04859/) (2022)
- [Multi-LexSum: Real-World Summaries of Civil Rights Lawsuits at Multiple Granularities](https://mlsanity.com/paper/2206.10883/) (2022)
- [BUSTLE: Bottom-Up Program Synthesis Through Learning-Guided Exploration](https://mlsanity.com/paper/2007.14381/) (2020)
- [Learning abstract structure for drawing by efficient motor program induction](https://mlsanity.com/paper/2008.03519/) (2020)
- [ACORD: An Expert-Annotated Retrieval Dataset for Legal Contract Drafting](https://mlsanity.com/paper/2501.06582/) (2025)
- [Computing and Exploiting Document Structure to Improve Unsupervised Extractive Summarization of Legal Case Decisions](https://mlsanity.com/paper/2211.03229/) (2022)

## Built on by (most cited first, 3 of 3)

- [LLM-Hanabi: Evaluating Multi-Agent Gameplays with Theory-of-Mind and Rationale Inference in Imperfect Information Collaboration Game](https://mlsanity.com/paper/2510.04980/) (2025)
- [Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Framework](https://mlsanity.com/paper/2508.12257/) (2025)
- [PL-CA: A Parametric Legal Case Augmentation Framework](https://mlsanity.com/paper/2509.06356/) (2025)

## Abstract (arXiv)

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 across jurisdictions. The advent of Large Language Models (LLMs) offers unprecedented potential to automate the extraction of such latent principles, yet progress is stymied by the absence of formal task definitions and benchmarks. To address this gap, we formalize Legal Rule Induction (LRI) as the task of deriving concise, generalizable doctrinal rules from analogous precedents, distilling their shared preconditions, normative behaviors, and legal consequences. We further propose a reproducible pipeline for LRI dataset construction and, instantiating it on Chinese law as a representative jurisdiction, introduce the first LRI benchmark comprising 5,121 case sets (38,088 court cases) 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.