A Neurosymbolic Approach to Natural Language Formalization and Verification
This addresses the need for reliable and auditable verification in industries like finance and healthcare, though it is an incremental improvement on existing neurosymbolic methods.
The paper tackles the problem of verifying natural language statements against strict policies in regulated industries by introducing a neurosymbolic framework that formalizes policies and validates logical correctness, achieving over 99% soundness in benchmarks.
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.