Using Large Language Models and Law-Based Rules for the Analysis of VAT Chain-Transaction Cases in Austrian Tax Law

In tax advisory practice, case descriptions are typically not structured in a machine-readable format, with clients describing their situation in natural language. Large language models excel at natural-language understanding. However, for legal reasoning, including tax law, the propensity of LLMs to hallucinate presents a considerable challenge. Rule-based systems, on the other hand, offer verifiably correct reasoning given the correct input. Therefore, in this paper, we propose a hybrid approach to support tax advisors with analyzing tax cases, combining a rule-based system with large language models. We focus on the analysis of chain-transaction cases in value-added tax (VAT) law, where the law states a clear set of rules for regular chain-transaction cases. We employ a large language model (LLM) for the construction of structured representations of natural-language VAT case descriptions and law-based rules for the identification of the movable supply, which determines tax liabilities. Human tax advisors can obtain a graphical visualization of the structured representation to verify the correctness of the LLM's output while the law-based rules return reliable decisions.

Keywords: Neuro-symbolic artificial intelligence, Knowledge graphs, Decision support systems, Tax management, Value-added tax.