Utilizing Large Language Models for Machine Learning Explainability
By: Alexandros Vassiliades , Nikolaos Polatidis , Stamatios Samaras and more
Potential Business Impact:
AI builds smart computer programs that explain themselves.
This study explores the explainability capabilities of large language models (LLMs), when employed to autonomously generate machine learning (ML) solutions. We examine two classification tasks: (i) a binary classification problem focused on predicting driver alertness states, and (ii) a multilabel classification problem based on the yeast dataset. Three state-of-the-art LLMs (i.e. OpenAI GPT, Anthropic Claude, and DeepSeek) are prompted to design training pipelines for four common classifiers: Random Forest, XGBoost, Multilayer Perceptron, and Long Short-Term Memory networks. The generated models are evaluated in terms of predictive performance (recall, precision, and F1-score) and explainability using SHAP (SHapley Additive exPlanations). Specifically, we measure Average SHAP Fidelity (Mean Squared Error between SHAP approximations and model outputs) and Average SHAP Sparsity (number of features deemed influential). The results reveal that LLMs are capable of producing effective and interpretable models, achieving high fidelity and consistent sparsity, highlighting their potential as automated tools for interpretable ML pipeline generation. The results show that LLMs can produce effective, interpretable pipelines with high fidelity and consistent sparsity, closely matching manually engineered baselines.
Similar Papers
LLMs for Explainable AI: A Comprehensive Survey
Artificial Intelligence
Makes confusing AI easy for people to understand.
Integration of Explainable AI Techniques with Large Language Models for Enhanced Interpretability for Sentiment Analysis
Computation and Language
Shows how computers understand feelings, layer by layer.
BELL: Benchmarking the Explainability of Large Language Models
Artificial Intelligence
Helps understand how smart computer programs think.