TaxoLogic is developing a hybrid AI framework that combines data-driven learning with logic-based reasoning to make regulatory decision-making processes transparent, explainable and verifiable.
In tax and compliance areas, current AI systems usually act as “black boxes” – efficient, but without comprehensible justification of their results. This lack of transparency poses considerable risks in legal areas such as tax law, where every decision must be consistent, comprehensible and legally sound. TaxoLogic closes this gap by combining the linguistic power of large language models (LLMs) with symbolic reasoning methods that guarantee logical consistency and traceability.
The focus of the project is on transfer pricing – a central challenge for multinational companies in the valuation of cross-border transactions. This requires the interpretation of sometimes contradictory sources such as OECD guidelines, national laws and bilateral agreements. TaxoLogic converts such texts into structured, machine-readable rules and applies logic-based procedures to derive coherent and verifiable interpretations. The framework provides both compliant results and transparent reasoning to support auditors, regulators and in-house counsel.
The project brings together eight complementary partners from science and industry: Steyr University of Applied Sciences and Vienna University of Economics and Business contribute tax law expertise, while the Research Institute for Symbolic Computation (JKU) and RISC Software GmbH conduct research into symbolic logic and hybrid architectures. Rise2Reality acts as a key technical and architectural partner with a focus on benchmarking LLMs for processing regulatory language and the practical implementation of the framework. The industry partners MIC, voestalpine and Greiner provide real data, use cases and validation scenarios from the areas of global trade, supply chains and corporate taxation. This composition ensures that the research results are both scientifically sound and practicable.
Once the project is completed, the results will be translated into pilot applications and market-ready products that integrate hybrid AI into control and compliance systems. This will enable companies to increase efficiency, reduce risks and position themselves in the market for transparent regulatory technologies. TaxoLogic promotes sustainable digital transformation through automation, better decision quality and explainable AI – and strengthens Europe’s technological sovereignty through the use of open, comprehensible AI components.
This project is funded by the Austrian Research Promotion Agency (FFG).
Data Scientist
