用大模型自动生成可解释的机器学习流程，效果媲美人工设计。
Utilizing Large Language Models for Machine Learning Explainability
- 让大模型自主设计机器学习训练流程
- 生成模型在精度与可解释性上表现优异，F1分数高
- 适合需要快速构建可解释模型的研究者
本研究探索大语言模型（LLMs）在自主生成机器学习解决方案时的可解释性能力。针对两类分类任务：(i) 驾驶员警觉状态二分类，(ii) 酵母数据集多标签分类。选用三种前沿LLM（OpenAI GPT、Anthropic Claude、DeepSeek），为其提示设计四种常见分类器（随机森林、XGBoost、多层感知机、LSTM）的训练流程。评估指标包括预测性能（召回率、精确率、F1分数）和可解释性，采用SHAP（SHapley Additive exPlanations）衡量平均SHAP保真度（模型输出与SHAP近似值间的均方误差）和平均SHAP稀疏性（被判定为重要特征的数量）。结果表明，LLMs能生成高效且可解释的模型，具备高保真度与稳定稀疏性，其表现接近人工设计基线，凸显其在自动化可解释机器学习流程生成中的潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。