arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.00079cs.HC
收藏

利用大语言模型增强SHAP值的可解释性

Enhancing the Interpretability of SHAP Values Using Large Language Models

Xianlong Zeng, Kewen Zhu

AI总结:

本文利用大语言模型提升SHAP值的可解释性,使非技术用户更易理解模型预测。

摘要:

模型可解释性对于理解并信任复杂机器学习模型(如XGBoost构建的模型)的决策至关重要。SHAP(SHapley Additive exPlanations)值已成为解释这些模型的流行工具,通过将输出归因于个体特征。然而,SHAP解释的技术性质往往限制了其在研究人员之外的实用性,使非技术终端用户难以理解模型的行为。为解决这一挑战,我们探索使用大语言模型(LLMs)将SHAP值输出翻译成通俗语言解释,以更易于非技术受众理解。通过应用预训练的LLM,我们生成的解释在保持SHAP值准确性的同时,显著提高了其清晰度和可操作性。我们的结果表明,LLM增强的SHAP解释能提供更直观的模型预测理解,从而提升机器学习模型的整体可解释性。未来的工作将探索进一步的定制、多模态解释和用户反馈机制以优化和扩展该方法。

英文摘要:

Model interpretability is crucial for understanding and trusting the decisions made by complex machine learning models, such as those built with XGBoost. SHAP (SHapley Additive exPlanations) values have become a popular tool for interpreting these models by attributing the output to individual features. However, the technical nature of SHAP explanations often limits their utility to researchers, leaving non-technical end-users struggling to understand the model's behavior. To address this challenge, we explore the use of Large Language Models (LLMs) to translate SHAP value outputs into plain language explanations that are more accessible to non-technical audiences. By applying a pre-trained LLM, we generate explanations that maintain the accuracy of SHAP values while significantly improving their clarity and usability for end users. Our results demonstrate that LLM-enhanced SHAP explanations provide a more intuitive understanding of model predictions, thereby enhancing the overall interpretability of machine learning models. Future work will explore further customization, multimodal explanations, and user feedback mechanisms to refine and expand the approach.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑