Software Engineering Methods For AI-Driven Deductive Legal Reasoning

Rohan Padhye
4/15/2024
cs.SEcs.CLcs.CY

No official code found. Best implementation: cmu-pasta/onward24 (0 stars, last commit 2024-06-27).

Abstract

The recent proliferation of generative artificial intelligence (AI) technologies such as pre-trained large language models (LLMs) has opened up new frontiers in computational law. An exciting area of development is the use of AI to automate the deductive rule-based reasoning inherent in statutory and contract law. This paper argues that such automated deductive legal reasoning can now be viewed from the lens of software engineering, treating LLMs as interpreters of natural-language programs with natural-language inputs. We show how it is possible to apply principled software engineering techniques to enhance AI-driven legal reasoning of complex statutes and to unlock new applications in automated meta-reasoning such as mutation-guided example generation and metamorphic property-based testing.

View on arXivView PDF

Code Implementations(1)

cmu-pasta/onward24Community100%

Artifacts associated with the Onward! 24 paper "Software Engineering Methods For AI-Driven Deductive Legal Reasoning"

00PythonJun 13, 20242 years ago

Similar Papers

On Verifiable Legal Reasoning: A Multi-Agent Framework with Formalized Knowledge Representations

83% match2025

Toward Robust Legal Text Formalization into Defeasible Deontic Logic using LLMs

82% match2025

Engineering the Law-Machine Learning Translation Problem: Developing Legally Aligned Models

82% match2025

An LLM Agentic Approach for Legal-Critical Software: A Case Study for Tax Prep Software

81% match2025

Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration

81% match1 repo92024

Specification languages for computational laws versus basic legal principles

81% match2025

Cite this paper

@article{padhye2024software,
  title  = {Software Engineering Methods For AI-Driven Deductive Legal Reasoning},
  author = {Rohan Padhye},
  year   = {2024},
  eprint = {2404.09868},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2404.09868v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2404.09868.svg)](https://codeofpaper.com/paper/2404.09868)

Discussion