大语言模型能否在信用风险模型中作为事后可解释性工具?
Could Large Language Models work as Post-hoc Explainability Tools in Credit Risk Models?
AI总结:
本文研究大语言模型是否能作为信用风险模型的事后可解释性接口,评估其在保持特征重要性排名和生成自主解释方面的能力。
摘要:
大语言模型(LLMs)在将基于模型的解释转化为人类可读的叙述方面展现出了潜力。本研究评估了LLMs在信用风险模型中作为事后可解释性接口的能力,重点在于其保持特征重要性排名和生成自主解释的能力。使用LendingClub数据集,我们比较了LLMs输出与SHAP和系数基于的归因方法在三个主要LLMs(包括GPT-4-turbo、Claude-Sonnet-4.5和Gemini-2.5-Flash)上的表现。结果表明,在受控提示下,LLMs能够可靠地重现参考排名,但在生成自主解释时显示出有限的对齐能力。这些发现表明,LLMs最佳用作叙述接口,而不是在信用风险治理中替代正式归因方法。
英文摘要:
Large language models (LLMs) have shown promise in translating model-based explanations into human-readable narratives. This study evaluates whether LLMs can serve as post-hoc explainability interfaces for credit risk models, focusing on their ability to preserve feature-importance rankings and generate autonomous explanations. Using a LendingClub dataset, we compare LLM outputs with SHAP and coefficient-based attributions on three major LLMs, including GPT-4-turbo, Claude-Sonnet-4.5, and Gemini-2.5-Flash. Results indicate that LLMs reliably reproduce reference rankings under controlled prompts but show limited alignment when generating explanations autonomously. These findings suggest that LLMs are best deployed as narrative interfaces rather than substitutes for formal attribution methods in credit risk governance.
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。