Automatic coherence-driven inference on arguments

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autore principale: Huntsman, Steve
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908554713104384
author Huntsman, Steve
author_facet Huntsman, Steve
contents Inconsistencies are ubiquitous in law, administration, and jurisprudence. Though a cure is too much to hope for, we propose a technological remedy. Large language models (LLMs) can accurately extract propositions from arguments and compile them into natural data structures that enable coherence-driven inference (CDI) via combinatorial optimization. This neurosymbolic architecture naturally separates concerns and enables meaningful judgments about the coherence of arguments that can inform legislative and policy analysis and legal reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2509_18523
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Automatic coherence-driven inference on arguments
Huntsman, Steve
Computers and Society
Artificial Intelligence
Inconsistencies are ubiquitous in law, administration, and jurisprudence. Though a cure is too much to hope for, we propose a technological remedy. Large language models (LLMs) can accurately extract propositions from arguments and compile them into natural data structures that enable coherence-driven inference (CDI) via combinatorial optimization. This neurosymbolic architecture naturally separates concerns and enables meaningful judgments about the coherence of arguments that can inform legislative and policy analysis and legal reasoning.
title Automatic coherence-driven inference on arguments
topic Computers and Society
Artificial Intelligence
url https://arxiv.org/abs/2509.18523