Utilizing Large Language Models for Machine Learning Explainability
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909831349141504 |
|---|---|
| author | Vassiliades, Alexandros Polatidis, Nikolaos Samaras, Stamatios Diplaris, Sotiris Martin, Ignacio Cabrera Manolopoulos, Yannis Vrochidis, Stefanos Kompatsiaris, Ioannis |
| author_facet | Vassiliades, Alexandros Polatidis, Nikolaos Samaras, Stamatios Diplaris, Sotiris Martin, Ignacio Cabrera Manolopoulos, Yannis Vrochidis, Stefanos Kompatsiaris, Ioannis |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_06912 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Utilizing Large Language Models for Machine Learning Explainability Vassiliades, Alexandros Polatidis, Nikolaos Samaras, Stamatios Diplaris, Sotiris Martin, Ignacio Cabrera Manolopoulos, Yannis Vrochidis, Stefanos Kompatsiaris, Ioannis Machine Learning 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. |
| title | Utilizing Large Language Models for Machine Learning Explainability |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.06912 |