Research

Paper

AI LLM February 20, 2026

Neurosymbolic Language Reasoning as Satisfiability Modulo Theory

Authors

Hyunseok Oh, Sam Stern, Youngki Lee, Matthai Philipose

Abstract

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.

Metadata

arXiv ID: 2602.18095
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-02-20
Fetched: 2026-02-23 05:33

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.18095v1</id>\n    <title>Neurosymbolic Language Reasoning as Satisfiability Modulo Theory</title>\n    <updated>2026-02-20T09:35:26Z</updated>\n    <link href='https://arxiv.org/abs/2602.18095v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.18095v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-02-20T09:35:26Z</published>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Hyunseok Oh</name>\n    </author>\n    <author>\n      <name>Sam Stern</name>\n    </author>\n    <author>\n      <name>Youngki Lee</name>\n    </author>\n    <author>\n      <name>Matthai Philipose</name>\n    </author>\n  </entry>"
}