Large Language Model Predicting the Corrosion Inhibition Efficiency Based on Text Embedding for Small Dataset

This repository contains the dataset and code for the manuscript "Large Language Model Predicting the Corrosion Inhibition Efficiency Based on Text Embedding for Small Dataset". File Structure: Code files: 5 independent scripts (A–E) corresponding to different experimental groups. Data files: 1 raw dataset used for training and prediction. README.md: Explanation of code implementation and data structure. allXGboost.md: Detailed reporting of all XGBoost hyperparameters for reproducibility across all groups (A–E).