用大模型增强决策树，让复杂判断既精准又可解释。
GPTree: Towards Explainable Decision-Making via LLM-powered Decision Trees
- 用大模型动态构建决策树，无需特征工程
- 识别初创独角兽的准确率提升至7.8%，超越GPT-4o
- 支持人工干预优化路径，适合需要可解释性的决策场景
传统决策树可解释性强但难以处理高维非线性数据，神经网络虽能捕捉复杂模式却牺牲可解释性。本文提出GPTree框架，结合决策树的可解释性与大模型的推理能力。GPTree无需特征工程和提示链，仅需任务提示即可通过树结构动态划分样本，并引入人机协同反馈机制，允许专家介入优化决策路径。实验表明，该方法在识别初创期‘独角兽’企业时达到7.8%的精确率，优于使用少样本学习的GPT-4o以及最佳人类决策者（3.1%~5.6%）。
原文摘要 · Abstract (English)
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%).
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。