A Neurosymbolic Approach to Natural Language Formalization and Verification
By: Sam Bayless , Stefano Buliani , Darion Cassel and more
Potential Business Impact:
Makes AI follow rules perfectly, like a robot lawyer.
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.
Similar Papers
Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Models
Artificial Intelligence
Teaches AI to think better and solve harder problems.
Enhancing Large Language Models through Neuro-Symbolic Integration and Ontological Reasoning
Artificial Intelligence
Makes AI answers more truthful and logical.
Intermediate Languages Matter: Formal Languages and LLMs affect Neurosymbolic Reasoning
Artificial Intelligence
Better AI reasoning by picking the right "thinking language."