Toward a Neuro-Symbolic Approach to Structure and Process International Tax Law
Where Has Legal Knowledge Gone: Constraining LLMs with Knowledge Graphs for Interpretable Reasoning
Zarja Hude is a PhD candidate at the London School of Economics and Political Science (LSE). Grounded in jurisprudence, her research explores how combining different AI techniques can approximate the legal reasoning process. She holds a Master's in corporate law from the University of Cambridge, where she graduated in 2023 and has remained active through "Hack the Law," an initiative that initially expanded CodeX's LLMxLaw Hackathon format and has since grown to include a conference and research competition. During her master's and PhD, she worked as a product manager at EY's Technology Centre of Excellence on generative AI applications in immigration law, a role she secured after winning a region-wide internal competition involving 136 teams from 29 countries. Her interest in legal data modelling began during her undergraduate studies, when she initiated a project to filter legal information for cross-border researchers that later received Horizon Europe funding.