Interpretable LLMs for Credit Risk: A Systematic Review and Taxonomy

TL;DR

This systematic review categorizes LLM-based credit risk assessment methods, emphasizing interpretability techniques, and identifies future research directions in the emerging field of AI-driven financial risk analysis.

Contribution

First comprehensive taxonomy of LLM approaches in credit risk, focusing on interpretability, based on analysis of 60 recent studies from 2020-2025.

Findings

Classified LLM architectures, data types, and explainability methods

Identified key trends and gaps in LLM-based credit scoring

Provided a structured overview for future research in AI finance

Abstract

Large Language Models (LLM), which have developed in recent years, enable credit risk assessment through the analysis of financial texts such as analyst reports and corporate disclosures. This paper presents the first systematic review and taxonomy focusing on LLMbased approaches in credit risk estimation. We determined the basic model architectures by selecting 60 relevant papers published between 2020-2025 with the PRISMA research strategy. And we examined the data used for scenarios such as credit default prediction and risk analysis. Since the main focus of the paper is interpretability, we classify concepts such as explainability mechanisms, chain of thought prompts and natural language justifications for LLM-based credit models. The taxonomy organizes the literature under four main headings: model architectures, data types, explainability mechanisms and application areas. Based on this analysis, we highlight the main future trends and research gaps for LLM-based credit scoring systems. This paper aims to be a reference paper for artificial intelligence and financial researchers.