测量大语言模型认为它们能做什么：SHAP忠实性与金融表格分类中的部署性
Measuring What LLMs Think They Do: SHAP Faithfulness and Deployability on Financial Tabular Classification
AI总结：
研究评估了LLMs在金融表格分类中的SHAP值，发现其自我解释与SHAP值存在分歧，指出LLMs在结构化金融建模中的局限性，但认为改进的可解释性机制可提升其在风险敏感领域的应用潜力。
摘要：
大型语言模型（LLMs）在分类任务中引起了广泛关注，通过零样本提示提供了一种灵活的替代方案，替代传统的受信任的经典机器学习模型，如LightGBM。然而，它们在结构化表格数据上的可靠性仍不清楚，尤其是在高风险应用如金融风险评估中。我们的研究系统地评估了LLMs并在金融分类任务中生成它们的SHAP值。我们的分析显示，LLMs对特征影响的自我解释与SHAP值之间存在分歧，以及LLMs与LightGBM的SHAP值之间有显著差异。这些发现突显了LLMs作为结构化金融建模独立分类器的局限性，但也传达了乐观的看法，即改进的可解释性机制结合少量样本提示将使LLMs在风险敏感领域中可用。
英文摘要：
Large Language Models (LLMs) have attracted significant attention for classification tasks, offering a flexible alternative to trusted classical machine learning models like LightGBM through zero-shot prompting. However, their reliability for structured tabular data remains unclear, particularly in high stakes applications like financial risk assessment. Our study systematically evaluates LLMs and generates their SHAP values on financial classification tasks. Our analysis shows a divergence between LLMs self-explanation of feature impact and their SHAP values, as well as notable differences between LLMs and LightGBM SHAP values. These findings highlight the limitations of LLMs as standalone classifiers for structured financial modeling, but also instill optimism that improved explainability mechanisms coupled with few-shot prompting will make LLMs usable in risk-sensitive domains.
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。
