2026-08-17T04:14:44.720Z http://ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai

ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai:3:12138 2026-08-06T19:26:23Z 3

ValidoAI Tax Regulation Search Module for Legal-Tax Orientation by Using GPT-Based Natural Language Models for Financial Analysis 2026 http://ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai/record/3/12138 https://link.springer.com/chapter/10.1007/978-3-032-24513-7_19 S. Milojković P. Dakić M. Aleksić Serbian entrepreneurs lack adequate information on tax laws and administrative procedures, which creates various problems for them and their bookkeeping company. This situation is exacerbated by inconsistent tax regulations and complex administrative processes. We developed ValidoAI, an innovative AI-based system with multiple modules addressing these challenges. The system automates tax-related processes and provides personalized guidance through natural language processing (NLP) models. The Tax Regulation Search (TRS) module helps small business owners understand their financial obligations through automated data visualization and analysis. The platform integrates essential functionalities, including employee-level payroll analysis, dynamic cash flow tracking, and structured interpretation of financial reports. The system’s architecture features containerized microservices with specialized preprocessing for Serbian language nuances across both Cyrillic and Latin scripts. System structure and functionality were modeled using the ArchiMate standard, enabling precise representation of business, application, and technology layers. Key functionalities include anomaly detection, supplier similarity identification, and analytical feedback generation through advanced NLP techniques, including word embeddings, vector-based classifications, and clustering algorithms. Testing was conducted through a GPT-powered interface enabling real-time interaction with accounting data. Evaluation demonstrates 92% accuracy, a 2.1-s response time (75% faster than manual consultation), and 4.2/5.0 user satisfaction through dual evaluation combining automated metrics and expert assessment. The system achieves accuracy comparable to human experts (92% vs 95%) for routine queries while providing scalable, language-inclusive solutions for Serbian tax compliance. However, the system has limitations in handling complex legal scenarios requiring expert validation. bookPart Springer 217 229 https://doi.org/10.1007/978-3-032-24513-7_19 Communications in Computer and Information Science