Paper: arXiv 2506.04290

Authors: Muhammed Golec, Maha AlabdulJalil

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.

Complexity vs Empirical Score

  • Math Complexity: 2.0/10
  • Empirical Rigor: 6.0/10
  • Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: This paper is a qualitative systematic review and taxonomy following PRISMA guidelines rather than an empirical or mathematical research study. It offers high clarity and completeness in organizing LLM-based credit risk literature, though math complexity is naturally minimal.

Research Flowchart

  flowchart TD
    A[Research Goal: Review & Taxonomy of Interpretable LLMs for Credit Risk] --> B[PRISMA Selection: Filter 60 Papers 2020-2025]
    B --> C[Data & Text Inputs: Financial Reports, Disclosures, Analyst Texts]
    C --> D[Analysis & Categorization: Architectures, Prompts & XAI Mechanisms]
    D --> E[Taxonomy Creation: Architectures, Data, Explainability & Applications]
    E --> F[Outcomes: Identified Research Gaps, Future Trends & Reference Framework]

Cited References (91)

  1. Game theory analysis on credit risk assessment in E-commerce (2022)
  2. Data-driven decision-making in credit risk management: The information value of analyst reports (2022)
  3. Comparative Investigation of GPT and FinBERT’s Sentiment Analysis Performance in News Across Different Sectors (2025)
  4. Innovative Sentiment Analysis and Prediction of Stock Price Using FinBERT, GPT-4 and Logistic Regression: A Data-Driven Approach (2024)
  5. A Review on Large Language Models and Generative AI in Banking
  6. Enhancing financial inclusion and regulatory challenges: A critical analysis of digital banks and alternative lenders through digital platforms, machine learning, and large language models integration (2024) — link
  7. Gen AI for Market Risk and Credit Risk Learn Agentically powered Gen AI; Gen AI Agentic Framework for Financial Risk Management (2025)
  8. A survey on large language models for critical societal domains: Finance, healthcare, and law (2024) — link
and 83 more
  1. A systematic review of sentiment analytics in banking headlines (2025)
  2. A survey of large language models for financial applications: Progress, prospects and challenges — → 2406.11903
  3. Machine Learning for Identifying Risk in Financial Statements: A Survey (2025)
  4. The role artificial intelligence in modern banking: an exploration of AI-driven approaches for enhanced fraud prevention, risk management, and regulatory compliance (2023)
  5. A Comprehensive Review of Gen AI Agents: Applications and Frameworks in Finance, Investments and Risk Domains (2025)
  6. Large Language Models for Financial and Investment Management: Applications and Benchmarks. (2024)
  7. Review of Gen AI Models for Financial Risk Management: Architectural Frameworks and Implementation Strategies (2025)
  8. Large Language Models in Finance (FinLLMs) (2025)
  9. Model-agnostic explainable artificial intelligence methods in finance: a systematic review, recent developments, limitations, challenges and future directions (2025)
  10. The impact of big data characteristics on credit risk assessment (2025)
  11. Large Language Models in Finance: Reasoning (2024)
  12. Large language models in finance: A survey (2023)
  13. Can llms be good financial advisors?: An initial study in personal decision making for optimized outcomes (2023) — link
  14. Comparative analysis of large language models adaptability to detect sentiments in financial domain
  15. Large Language Models (LLMs) for Financial Security (2024)
  16. Assessing Consistency and Reproducibility in the Outputs of Large Language Models: Evidence Across Diverse Finance and Accounting Tasks (2025)
  17. Large language models and generative AI in finance: an analysis of ChatGPT, Bard, and Bing AI (2023)
  18. GenAI and LLM for Financial Institutions: A Corporate Strategic Survey (2024)
  19. Instruct-fingpt: Financial sentiment analysis by instruction tuning of general-purpose large language models — → 2306.12659
  20. Enhancing Auto Insurance Risk Evaluation with Transformer and SHAP (2024)
  21. Machine Learning in Credit Risk Assessment: A Comparative Analysis of Different Models (2024)
  22. FinBERT: A large language model for extracting information from financial text (2023)
  23. Credit Risk Meets Large Language Models: Building a Risk Indicator from Loan Descriptions in P2P Lending — → 2401.16458
  24. NLP-Based application for analyzing private and public banks stocks reaction to news events in the Indian stock exchange (2022)
  25. Extracting structured insights from financial news: An augmented llm driven approach (2024) — link
  26. Overcoming Data Limitations in Credit Risk Assessment with FinGPT-Generated Synthetic Data (2024)
  27. Explainable transformers in financial forecasting (2023)
  28. Pixiu: A large language model, instruction data and evaluation benchmark for finance (2023) — link
  29. GPT classifications, with application to credit lending (2024)
  30. Making llms worth every penny: Resource-limited text classification in banking (2023)
  31. Leveraging XAI in Prompt-Based ChatGPT for Financial Decision Support (2024)
  32. Hallucination detection: Robustly discerning reliable answers in large language models (2023)
  33. OPTIMIZING LARGE LANGUAGE MODELS FOR FINANCIAL RISK ASSESSMENT IN CREDIT UNIONS (2024)
  34. Large language model adaptation for financial sentiment analysis (2024) — link
  35. Generating plausible counterfactual explanations for deep transformers in financial text classification (2020) — link
  36. Deep Learning with LLM: A New Paradigm for Financial Market Prediction and Analysis (2025)
  37. Design and Implementation of an LLM system to Improve Response Time for SMEs Technology Credit Evaluation (2023)
  38. Empowering many, biasing a few: Generalist credit scoring through large language models (2023) — link
  39. OPTIMIZING LARGE LANGUAGE MODELS FOR FINANCIAL RISK ASSESSMENT IN CREDIT UNIONS
  40. Predicting Liquidity-Aware Bond Yields using Causal GANs and Deep Reinforcement Learning with LLM Evaluation — → 2502.17011
  41. Explainable risk classification in financial reports — → 2405.01881
  42. Investigating the beneficial impact of segmentation-based modelling for credit scoring (2024)
  43. Instruct-fingpt: Financial sentiment analysis by instruction tuning of general-purpose large language models — → 2306.12659
  44. AraFinNlp 2024: The first arabic financial nlp shared task (2024) — link
  45. Unleashing the power of text for credit default prediction: Comparing human-generated and AI-generated texts (2023)
  46. Bankruptcy Prediction: Data Augmentation, LLMs and the Need for Auditor’s Opinion (2024)
  47. A Comparative Analysis of Instruction Fine-Tuning LLMs for Financial Text Classification (2024) — link
  48. Scalable fine-tunning strategies for llms in finance domain-specific application for credit union (2024)
  49. Open FinLLM leaderboard: Towards financial ai readiness (2025) — link
  50. ZiGong 1.0: A Large Language Model for Financial Credit (2025) — link
  51. Llms for financial advisement: A fairness and efficacy study in personal decision making (2023)
  52. Data-centric fingpt: Democratizing internet-scale data for financial large language models (2023)
  53. Bridging Language Models and Financial Analysis — → 2503.22693
  54. Pixiu: A large language model, instruction data and evaluation benchmark for finance (2023) — link
  55. Advanced Default Risk Prediction in Small and Medum-Sized Enterprises Using Large Language Models (2025)
  56. Tagging Enriched Bank Transactions Using LLM-Generated Topic Taxonomies (2024)
  57. Open-finllms: Open multimodal large language models for financial applications — → 2408.11878
  58. Dynamic financial sentiment analysis and market forecasting through large language models (2025)
  59. GPT classifications, with application to credit lending (2024)
  60. Leveraging Internet-Sourced Text Data for Financial Analytics in Supply Chain Finance: A Large Language Model-Enhanced Text Mining Workflow (2025)
  61. ChatGPT based credit rating and default forecasting (2025)
  62. A Novel Weighted Loss TabTransformer Integrating Explainable AI for Imbalanced Credit Risk Datasets (2025)
  63. Leveraging Large Language Models for Enhancing Financial Compliance: A Focus on Anti-Money Laundering Applications (2024)
  64. Systematic Evaluation of Long-Context LLMs on Financial Concepts (2024) — link
  65. Analyse Customer Behaviour and Sentiment Using Natural Language Processing (NLP) Techniques to Improve Customer Service and Personalize Banking Experiences (2024)
  66. Harnessing earnings reports for stock predictions: A qlora-enhanced llm approach (2024)
  67. Large language models and financial market sentiment (2023)
  68. Enhancing Auto Insurance Risk Evaluation with Transformer and SHAP (2024)
  69. Identifying Representation Bias in Large Language Models Used in Financial Sentiment Analysis (2025)
  70. Finben: A holistic financial benchmark for large language models (2024)
  71. Research on the Application Methods of Large Language Model Interpretability in FinTech Scenarios (2024)
  72. AT-FinGPT: Financial risk prediction via an audio-text large language model (2025)
  73. Secured framework for banking Chatbots using AI, ML and NLP (2023)
  74. AI in Investment Analysis: LLMs for Equity Stock Ratings (2024)
  75. Sentiment analysis in finance: From transformers back to explainable lexicons (xlex) (2024)
  76. Understanding behaviour of large language models for short-term and long-term fairness scenarios (2023)
  77. Gpt-Lgbm: A Chatgpt-Based Integrated Framework for Credit Scoring with Textual and Structured Data (2023)
  78. LLMs analyzing the analysts: Do BERT and GPT extract more value from financial analyst reports? (2023)
  79. Credit Risk Meets Large Language Models: Building a Risk Indicator from Loan Descriptions in Peer-to-Peer Lending
  80. Is chatgpt a financial expert? evaluating language models on financial natural language processing (2023) — link
  81. Beyond Black-Box AI: A Theory of Interpretable Transformers for Asset Pricing (2025)
  82. Enhancing financial sentiment analysis via retrieval augmented large language models — → 2310.04027
  83. LLM-Driven APT Detection for 6G Wireless Networks: A Systematic Review and Taxonomy (2025) — link

9 of 91 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.