Author(s)

Thomas Eriksson, Karin Olsson^*

Affiliation(s)

Department of Business Studies, Uppsala University, Uppsala, Sweden.

Corresponding Author

Karin Olsson

ABSTRACT

The complexity and opacity of modern tax systems present significant challenges for individuals and small businesses during tax preparation. In recent years, large language models (LLMs) have demonstrated the potential to understand, interpret, and generate human-like language at scale. This paper proposes a user-centric framework that leverages LLMs to enhance tax preparation through personalized assistance, error detection, regulatory compliance guidance, and intelligent document analysis. We analyze the capabilities and limitations of current LLMs, present a system architecture for integrating these models into tax platforms, and evaluate their performance using simulated taxpayer scenarios. The framework emphasizes explainability, privacy protection, and real-time adaptability to user input. Results indicate that LLMs significantly reduce user burden, improve accuracy, and foster greater financial literacy. The findings highlight the transformative potential of language-based AI to democratize access to complex tax knowledge and reduce dependency on traditional, costly tax advisory services.

KEYWORDS

Tax Preparation; Large Language Models; User-Centric Design; Financial AI; Document Processing; Explainable AI; Human-AI Interaction

CITE THIS PAPER

Thomas Eriksson, Karin Olsson. Enhancing tax preparation through large language models: a user-centric framework. Journal of Trends in Financial and Economics. 2025, 2(3): 1-6. DOI: https://doi.org/10.61784/jtfe3048.

REFERENCES

[1] Singireddy J. AI-Enhanced Tax Preparation and Filing: Automating Complex Regulatory Compliance. European Data Science Journal (EDSJ), 2024, 2(1).

[2] Li P, Ren S, Zhang Q, et al. Think4SCND: Reinforcement Learning with Thinking Model for Dynamic Supply Chain Network Design. IEEE Access, 2024.

[3] Davenport MJ. Enhancing Legal Document Analysis with Large Language Models: A Structured Approach to Accuracy, Context Preservation, and Risk Mitigation. Open Journal of Modern Linguistics, 2025, 15(2): 232-280.

[4] Ren S, Jin J, Niu G, et al. ARCS: Adaptive Reinforcement Learning Framework for Automated Cybersecurity Incident Response Strategy Optimization. Applied Sciences, 2025, 15(2): 951.

[5] Shao Z, Wang X, Ji E, et al. GNN-EADD: Graph Neural Network-based E-commerce Anomaly Detection via Dual-stage Learning. IEEE Access, 2025.

[6] Olabanji SO. Technological tools in facilitating cryptocurrency tax compliance: An exploration of software and platforms supporting individual and business adherence to tax norms. Available at SSRN 4600838, 2023.

[7] Sabry F. Income Tax: Mastering Income Tax, Your Path to Financial Empowerment (Vol. 188). One Billion Knowledgeable, 2024.

[8] Chen S, Liu Y, Zhang Q, et al. Multi-Distance Spatial-Temporal Graph Neural Network for Anomaly Detection in Blockchain Transactions. Advanced Intelligent Systems, 2025, 2400898.

[9] Rahman S, Sirazy MRM, Das R, et al. An exploration of artificial intelligence techniques for optimizing tax compliance, fraud detection, and revenue collection in modern tax administrations. International Journal of Business Intelligence and Big Data Analytics, 2024, 7(3): 56-80.

[10] Wang J, Tan Y, Jiang B, et al. Dynamic Marketing Uplift Modeling: A Symmetry-Preserving Framework Integrating Causal Forests with Deep Reinforcement Learning for Personalized Intervention Strategies. Symmetry, 2025, 17(4): 610.

[11] Johnsen R. Large language models (LLMs). Maria Johnsen, 2024.

[12] Zafar A, Parthasarathy VB, Van CL, et al. Building trust in conversational AI: A comprehensive review and solution architecture for explainable, privacy-aware systems using LLMs and knowledge graph. arXiv preprint arXiv:2308.13534, 2023.

[13] Nay JJ, Karamardian D, Lawsky SB, et al. Large language models as tax attorneys: a case study in legal capabilities emergence. Philosophical Transactions of the Royal Society A, 2024, 382(2270): 20230159.

[14] Singh V. Fostering Effective Human-AI Collaboration: Bridging the Gap Between User-Centric Design and Ethical Implementation. International Journal on Recent and Innovation Trends in Computing and Communication, 2024, 12(2): 22-30.

[15] Aidonojie PA, Majekodunmi TA, Eregbuonye O, et al. Legal Issues Concerning of Data Security and Privacy in Automated Income Tax Systems in Nigeria. Hang Tuah Law Journal, 2024: 14-41.

[16] Bezditnyi V. Use of artificial intelligence for tax planning optimization and regulatory compliance. Research Corridor Journal of Engineering Science, 2024, 1(1): 103-142.

[17] Ghosh B, Ghosh A, Ghosh S, et al. An Analytical Study of Text Summarization Techniques. In: International IOT, Electronics and Mechatronics Conference, Singapore: Springer Nature Singapore, 2024: 351-363.

[18] Mohun J, Roberts A. Cracking the code: Rulemaking for humans and machines. OECD Working Papers on Public Governance, 2020(42): 0_1-109.

[19] Singireddy J. Smart Finance: Harnessing Artificial Intelligence to Transform Tax, Accounting, Payroll, and Credit Management for the Digital Age. Deep Science Publishing, 2025.

[20] Hassija V, Chamola V, Mahapatra A, et al. Interpreting black-box models: a review on explainable artificial intelligence. Cognitive Computation, 2024, 16(1): 45-74.

[21] Desai B, Patil K, Patil A, et al. Large Language Models: A Comprehensive Exploration of Modern AI's Potential and Pitfalls. Journal of Innovative Technologies, 2023, 6(1).

[22] Tan Y, Wu B, Cao J, et al. LLaMA-UTP: Knowledge-Guided Expert Mixture for Analyzing Uncertain Tax Positions. IEEE Access, 2025.

[23] Siino M, Falco M, Croce D, et al. Exploring LLMs Applications in Law: A Literature Review on Current Legal NLP Approaches. IEEE Access, 2025.

[24] Strak T. Generative AI as tax attorneys: exploring legal understanding through experiments, 2024.

[25] Srinivas D, Das R, Tizpaz-Niari S, et al. On the potential and limitations of few-shot in-context learning to generate metamorphic specifications for tax preparation software. arXiv preprint arXiv:2311.11979, 2023.

[26] Qatawneh AM. The role of artificial intelligence in auditing and fraud detection in accounting information systems: moderating role of natural language processing. International Journal of Organizational Analysis, 2024.

[27] Benkel A. Using Large Language Models for Legal Decision Making in Austrian Value-Added Tax Law: an Experimental Investigation of Retrieval-Augmented Generation and Fine-Tuning. Submitted, 2025.

[28] Mumuni F, Mumuni A. Explainable artificial intelligence (XAI): from inherent explainability to large language models. arXiv preprint arXiv:2501.09967, 2025.

[29] Elsayed RAA. The impact of ontology-based knowledge management on improving tax accounting procedures and reducing tax risks. Future Business Journal, 2023, 9(1): 70.

[30] Fang Z. Adaptive QoS‐Aware Cloud–Edge Collaborative Architecture for Real‐Time Smart Water Service Management, 2025.

[31] Ballas P, Hyz A, Balla VM. Enhancing Social and Economic Resilience for a Changing World: The Strategic Role of Continuous Training and Capacity Building in Contemporary Tax and Customs Administrations. In: The Role of the Public Sector in Building Social and Economic Resilience: A Public Finance Approach. Cham: Springer Nature Switzerland, 2024: 157-179.

[32] Ault HJ, Arnold BJ, Cooper GS. Comparative income taxation: a structural analysis. Kluwer Law International BV, 2025.

[33] Yang Y, Wang M, Wang J, et al. Multi-Agent Deep Reinforcement Learning for Integrated Demand Forecasting and Inventory Optimization in Sensor-Enabled Retail Supply Chains. Sensors (Basel, Switzerland), 2025, 25(8): 2428.

[34] Abdul Rashid SF, Sanusi S, Abu Hassan NS. Digital Transformation: Confronting Governance, Sustainability, and Taxation Challenges in an Evolving Digital Landscape. In: Corporate Governance and Sustainability: Navigating Malaysia's Business Landscape. Singapore: Springer Nature Singapore, 2024: 125-144.

[35] Jin J, Xing S, Ji E, et al. XGate: Explainable Reinforcement Learning for Transparent and Trustworthy API Traffic Management in IoT Sensor Networks. Sensors (Basel, Switzerland), 2025, 25(7): 2183.