LML-DAP: Language Model Learning a Dataset for Data-Augmented Prediction

TL;DR

This paper presents LML-DAP, a novel approach using Large Language Models for explainable, data-augmented classification that achieves high accuracy and reduces reliance on traditional feature engineering.

Contribution

It introduces the LML-DAP framework, combining dataset summarization and context-aware querying to enhance explainability and performance in classification tasks.

Findings

Achieved over 90% accuracy in test cases

Provides explainable and context-aware classification

Reduces need for data cleaning and feature engineering

Abstract

Classification tasks are typically handled using Machine Learning (ML) models, which lack a balance between accuracy and interpretability. This paper introduces a new approach for classification tasks using Large Language Models (LLMs) in an explainable method. Unlike ML models, which rely heavily on data cleaning and feature engineering, this method streamlines the process using LLMs. This paper proposes a method called "Language Model Learning (LML)" powered by a new method called "Data-Augmented Prediction (DAP)." The classification is performed by LLMs using a method similar to that used by humans who manually explore and understand the data to decide classifications. In the process of LML, a dataset is summarized and evaluated to determine the features leading to each label the most. In the DAP process, the system uses the data summary and a row of the testing dataset to automatically generate a query to retrieve relevant rows from the dataset for context-aware classification. LML and DAP unlock new possibilities in areas that require explainable and context-aware decisions by ensuring satisfactory accuracy even with complex data. The system scored an accuracy above 90% in some test cases, confirming the effectiveness and potential of the system to outperform ML models in various scenarios. The source code is available at https://github.com/Pro-GenAI/LML-DAP