Towards Robust Legal Reasoning: Harnessing Logical LLMs in Law

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kant, Manuj, Nabi, Sareh, Kant, Manav, Scharrer, Roland, Ma, Megan, Nabi, Marzieh
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915171303161856
author Kant, Manuj
Nabi, Sareh
Kant, Manav
Scharrer, Roland
Ma, Megan
Nabi, Marzieh
author_facet Kant, Manuj
Nabi, Sareh
Kant, Manav
Scharrer, Roland
Ma, Megan
Nabi, Marzieh
contents Legal services rely heavily on text processing. While large language models (LLMs) show promise, their application in legal contexts demands higher accuracy, repeatability, and transparency. Logic programs, by encoding legal concepts as structured rules and facts, offer reliable automation, but require sophisticated text extraction. We propose a neuro-symbolic approach that integrates LLMs' natural language understanding with logic-based reasoning to address these limitations. As a legal document case study, we applied neuro-symbolic AI to coverage-related queries in insurance contracts using both closed and open-source LLMs. While LLMs have improved in legal reasoning, they still lack the accuracy and consistency required for complex contract analysis. In our analysis, we tested three methodologies to evaluate whether a specific claim is covered under a contract: a vanilla LLM, an unguided approach that leverages LLMs to encode both the contract and the claim, and a guided approach that uses a framework for the LLM to encode the contract. We demonstrated the promising capabilities of LLM + Logic in the guided approach.
format Preprint
id arxiv_https___arxiv_org_abs_2502_17638
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Robust Legal Reasoning: Harnessing Logical LLMs in Law
Kant, Manuj
Nabi, Sareh
Kant, Manav
Scharrer, Roland
Ma, Megan
Nabi, Marzieh
Computers and Society
Artificial Intelligence
Legal services rely heavily on text processing. While large language models (LLMs) show promise, their application in legal contexts demands higher accuracy, repeatability, and transparency. Logic programs, by encoding legal concepts as structured rules and facts, offer reliable automation, but require sophisticated text extraction. We propose a neuro-symbolic approach that integrates LLMs' natural language understanding with logic-based reasoning to address these limitations. As a legal document case study, we applied neuro-symbolic AI to coverage-related queries in insurance contracts using both closed and open-source LLMs. While LLMs have improved in legal reasoning, they still lack the accuracy and consistency required for complex contract analysis. In our analysis, we tested three methodologies to evaluate whether a specific claim is covered under a contract: a vanilla LLM, an unguided approach that leverages LLMs to encode both the contract and the claim, and a guided approach that uses a framework for the LLM to encode the contract. We demonstrated the promising capabilities of LLM + Logic in the guided approach.
title Towards Robust Legal Reasoning: Harnessing Logical LLMs in Law
topic Computers and Society
Artificial Intelligence
url https://arxiv.org/abs/2502.17638