Score: 0

A Neurosymbolic Approach to Natural Language Formalization and Verification

Published: November 12, 2025 | arXiv ID: 2511.09008v1

By: Sam Bayless , Stefano Buliani , Darion Cassel and more

Potential Business Impact:

Makes AI follow rules perfectly, like a robot lawyer.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

Large Language Models perform well at natural language interpretation and reasoning, but their inherent stochasticity limits their adoption in regulated industries like finance and healthcare that operate under strict policies. To address this limitation, we present a two-stage neurosymbolic framework that (1) uses LLMs with optional human guidance to formalize natural language policies, allowing fine-grained control of the formalization process, and (2) uses inference-time autoformalization to validate logical correctness of natural language statements against those policies. When correctness is paramount, we perform multiple redundant formalization steps at inference time, cross checking the formalizations for semantic equivalence. Our benchmarks demonstrate that our approach exceeds 99% soundness, indicating a near-zero false positive rate in identifying logical validity. Our approach produces auditable logical artifacts that substantiate the verification outcomes and can be used to improve the original text.

Page Count
20 pages

Category
Computer Science:
Computation and Language