对比大模型自解释与真实特征重要性，发现其金融分类不可靠
Measuring What LLMs Think They Do: SHAP Faithfulness and Deployability on Financial Tabular Classification
- 用SHAP分析大模型对金融表格数据的特征影响
- 大模型自述重要性与实际SHAP值偏差显著
- 适合关注模型可解释性的金融风控研究者
大语言模型（LLMs）在分类任务中备受关注，通过零样本提示提供灵活替代方案，但其在结构化表格数据上的可靠性仍不明确，尤其在金融风险评估等高风险场景。本研究系统评估了LLMs在金融分类任务中的表现，并生成其SHAP值。分析显示，LLMs的自我解释（特征重要性）与其实际SHAP值存在显著差异，且与经典模型LightGBM的SHAP值也明显不同。这些发现揭示了LLMs作为独立分类器在结构化金融建模中的局限性，但也表明通过改进可解释性机制结合少量样本提示，未来有望在风险敏感领域应用。
原文摘要 · Abstract (English)
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.
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。