GPTree: Towards Explainable Decision-Making via LLM-powered Decision Trees
This work addresses the need for explainable AI in high-stakes domains like startup investment, offering a novel hybrid approach that balances accuracy and interpretability.
The paper tackles the problem of explainable decision-making in complex data by proposing GPTree, a framework that combines decision trees with LLMs, achieving a 7.8% precision rate for identifying unicorn startups, outperforming GPT-4o and human experts.
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%).