Building Trustworthy AI: Transparent AI Systems via Large Language Models, Ontologies, and Logical Reasoning (TranspNet)
It addresses the problem of AI transparency for high-stakes applications, offering an incremental improvement by combining existing methods like LLMs, ontologies, and logical reasoning.
The paper tackled the lack of transparency in AI systems, particularly in high-stakes fields like healthcare and finance, by proposing the TranspNet pipeline that integrates symbolic AI with Large Language Models to enhance outputs with structured reasoning and verification, aiming to make AI more explainable and trustworthy.
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.