Explaining Genetic Programming Trees using Large Language Models
Paula Maddigan, Andrew Lensen, Bing Xue
TL;DR
This paper addresses the challenge of making GP-based nonlinear dimensionality reduction results interpretable for diverse users. It introduces GP4NLDR, a web-based dashboard that blends GP-NLDR with an LLM-powered chatbot and retrieval augmented generation to deliver user-centered, natural-language explanations of GP trees and embeddings. The approach combines prompt engineering, LangChain integration, and FAISS-based RAG to mitigate hallucinations and provide context-aware responses, demonstrated on Wine, Dermatology, and COIL-20 case studies. The work advances explainable GP by offering an accessible, interactive tool and highlights future research directions including human evaluations and broader GP applications.
Abstract
Genetic programming (GP) has the potential to generate explainable results, especially when used for dimensionality reduction. In this research, we investigate the potential of leveraging eXplainable AI (XAI) and large language models (LLMs) like ChatGPT to improve the interpretability of GP-based non-linear dimensionality reduction. Our study introduces a novel XAI dashboard named GP4NLDR, the first approach to combine state-of-the-art GP with an LLM-powered chatbot to provide comprehensive, user-centred explanations. We showcase the system's ability to provide intuitive and insightful narratives on high-dimensional data reduction processes through case studies. Our study highlights the importance of prompt engineering in eliciting accurate and pertinent responses from LLMs. We also address important considerations around data privacy, hallucinatory outputs, and the rapid advancements in generative AI. Our findings demonstrate its potential in advancing the explainability of GP algorithms. This opens the door for future research into explaining GP models with LLMs.