Delta1 with LLM: symbolic and neural integration for credible and explainable reasoning
This work addresses the need for credible and explainable neuro-symbolic reasoning, particularly in high-stakes domains like healthcare and compliance, though it appears incremental in integrating existing components.
The paper tackles the problem of integrating formal logic with large language models for explainable reasoning by introducing a pipeline that combines the Automated Theorem Generator Delta1 with LLMs to generate minimal unsatisfiable clause sets and verbalize proofs into natural language explanations, with empirical studies in healthcare, compliance, and regulatory domains showing it enables interpretable and auditable reasoning.
Neuro-symbolic reasoning increasingly demands frameworks that unite the formal rigor of logic with the interpretability of large language models (LLMs). We introduce an end to end explainability by construction pipeline integrating the Automated Theorem Generator Delta1 based on the full triangular standard contradiction (FTSC) with LLMs. Delta1 deterministically constructs minimal unsatisfiable clause sets and complete theorems in polynomial time, ensuring both soundness and minimality by construction. The LLM layer verbalizes each theorem and proof trace into coherent natural language explanations and actionable insights. Empirical studies across health care, compliance, and regulatory domains show that Delta1 and LLM enables interpretable, auditable, and domain aligned reasoning. This work advances the convergence of logic, language, and learning, positioning constructive theorem generation as a principled foundation for neuro-symbolic explainable AI.