GPTree: Towards Explainable Decision-Making via LLM-powered Decision Trees

TL;DR

GPTree integrates explainable decision trees with LLMs to improve complex decision-making, eliminating feature engineering and incorporating human feedback, achieving superior precision in startup identification.

Contribution

This work introduces GPTree, a novel framework that combines LLM-powered decision trees with human-in-the-loop feedback for enhanced explainability and performance.

Findings

Achieved 7.8% precision in identifying 'unicorn' startups.

Outperformed GPT-4o with few-shot learning and top human decision-makers.

Eliminated need for feature engineering and prompt chaining.

Abstract

Traditional decision tree algorithms are explainable but struggle with non-linear, high-dimensional data, limiting its applicability in complex decision-making. Neural networks excel at capturing complex patterns but sacrifice explainability in the process. In this work, we present GPTree, a novel framework combining explainability of decision trees with the advanced reasoning capabilities of LLMs. GPTree eliminates the need for feature engineering and prompt chaining, requiring only a task-specific prompt and leveraging a tree-based structure to dynamically split samples. We also introduce an expert-in-the-loop feedback mechanism to further enhance performance by enabling human intervention to refine and rebuild decision paths, emphasizing the harmony between human expertise and machine intelligence. Our decision tree achieved a 7.8% precision rate for identifying "unicorn" startups at the inception stage of a startup, surpassing gpt-4o with few-shot learning as well as the best human decision-makers (3.1% to 5.6%).