Building Trustworthy AI: Transparent AI Systems via Large Language Models, Ontologies, and Logical Reasoning (TranspNet)

TL;DR

TranspNet is a novel pipeline that combines Large Language Models, ontologies, and logical reasoning to improve transparency, explainability, and trustworthiness of AI systems in high-stakes domains.

Contribution

The paper introduces TranspNet, a framework integrating symbolic AI with LLMs using domain knowledge, retrieval-augmented generation, and formal reasoning to enhance AI transparency and verification.

Findings

TranspNet improves AI output explainability and trustworthiness.

The framework effectively verifies LLM-generated results.

TranspNet is suitable for high-stakes real-world applications.

Abstract

Growing concerns over the lack of transparency in AI, particularly in high-stakes fields like healthcare and finance, drive the need for explainable and trustworthy systems. While Large Language Models (LLMs) perform exceptionally well in generating accurate outputs, their "black box" nature poses significant challenges to transparency and trust. To address this, the paper proposes the TranspNet pipeline, which integrates symbolic AI with LLMs. By leveraging domain expert knowledge, retrieval-augmented generation (RAG), and formal reasoning frameworks like Answer Set Programming (ASP), TranspNet enhances LLM outputs with structured reasoning and verification.This approach strives to help AI systems deliver results that are as accurate, explainable, and trustworthy as possible, aligning with regulatory expectations for transparency and accountability. TranspNet provides a solution for developing AI systems that are reliable and interpretable, making it suitable for real-world applications where trust is critical.