AI RESEARCH
Could Large Language Models work as Post-hoc Explainability Tools in Credit Risk Models?
arXiv CS.LG
•
ArXi:2602.18895v2 Announce Type: replace-cross 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.