Could Large Language Models work as Post-hoc Explainability Tools in Credit Risk Models?

2026-02-21 · Wenxi Geng, Dingyuan Liu, Liya Li, Yiqing Wang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2602.18895

Code (0)

등록된 구현이 없습니다.

Monetizing Currency Pair Sentiments through LLM Explainability

2024-07-29 · Lior Limonad, Fabiana Fournier, Juan Manuel Vera Díaz, Inna Skarbovsky 외

Large language models (LLMs) play a vital role in almost every domain in today's organizations. In the context of this work, we highlight the use of LLMs for sentiment analysis (SA) and explainability. Specifically, we c…

Sentiment Analysis

XCM: An Explainable Convolutional Neural Network for Multivariate Time Series Classification

2020-09-10 · Kevin Fauvel, Tao Lin, Véronique Masson, Élisa Fromont 외

Multivariate Time Series (MTS) classification has gained importance over the past decade with the increase in the number of temporal datasets in multiple domains. The current state-of-the-art MTS classifier is a heavywei…

General Classification Time Series Time Series Analysis Time Series Classification

Explainability in Deep Reinforcement Learning

2020-08-15 · Alexandre Heuillet, Fabien Couthouis, Natalia Díaz-Rodríguez

A large set of the explainable Artificial Intelligence (XAI) literature is emerging on feature relevance techniques to explain a deep neural network (DNN) output or explaining models that ingest image source data. Howeve…

Deep Reinforcement Learning Explainable artificial intelligence Explainable Artificial Intelligence (XAI)reinforcement-learning+2

When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing

2025-08-14 · Mahdi Dhaini, Stephen Meisenbacher, Ege Erdogan, Florian Matthes 외 arxiv

In the study of trustworthy Natural Language Processing (NLP), a number of important research fields have emerged, including that of explainability and privacy. While research interest in both explainable and privacy-pre…

Explainable AI Reloaded: Challenging the XAI Status Quo in the Era of Large Language Models

2024-08-09 · Upol Ehsan, Mark O. Riedl

When the initial vision of Explainable (XAI) was articulated, the most popular framing was to open the (proverbial) "black-box" of AI so that we could understand the inner workings. With the advent of Large Language Mode…