Saved in:
Bibliographic Details
Main Authors: Oh, Hyunseok, Stern, Sam, Lee, Youngki, Philipose, Matthai
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.18095
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908843432214528
author Oh, Hyunseok
Stern, Sam
Lee, Youngki
Philipose, Matthai
author_facet Oh, Hyunseok
Stern, Sam
Lee, Youngki
Philipose, Matthai
contents Natural language understanding requires interleaving textual and logical reasoning, yet large language models often fail to perform such reasoning reliably. Existing neurosymbolic systems combine LLMs with solvers but remain limited to fully formalizable tasks such as math or program synthesis, leaving natural documents with only partial logical structure unaddressed. We introduce Logitext, a neurosymbolic language that represents documents as natural language text constraints (NLTCs), making partial logical structure explicit. We develop an algorithm that integrates LLM-based constraint evaluation with satisfiability modulo theory (SMT) solving, enabling joint textual-logical reasoning. Experiments on a new content moderation benchmark, together with LegalBench and Super-Natural Instructions, show that Logitext improves both accuracy and coverage. This work is the first that treats LLM-based reasoning as an SMT theory, extending neurosymbolic methods beyond fully formalizable domains.
format Preprint
id arxiv_https___arxiv_org_abs_2602_18095
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Neurosymbolic Language Reasoning as Satisfiability Modulo Theory
Oh, Hyunseok
Stern, Sam
Lee, Youngki
Philipose, Matthai
Artificial Intelligence
Natural language understanding requires interleaving textual and logical reasoning, yet large language models often fail to perform such reasoning reliably. Existing neurosymbolic systems combine LLMs with solvers but remain limited to fully formalizable tasks such as math or program synthesis, leaving natural documents with only partial logical structure unaddressed. We introduce Logitext, a neurosymbolic language that represents documents as natural language text constraints (NLTCs), making partial logical structure explicit. We develop an algorithm that integrates LLM-based constraint evaluation with satisfiability modulo theory (SMT) solving, enabling joint textual-logical reasoning. Experiments on a new content moderation benchmark, together with LegalBench and Super-Natural Instructions, show that Logitext improves both accuracy and coverage. This work is the first that treats LLM-based reasoning as an SMT theory, extending neurosymbolic methods beyond fully formalizable domains.
title Neurosymbolic Language Reasoning as Satisfiability Modulo Theory
topic Artificial Intelligence
url https://arxiv.org/abs/2602.18095