View PDF (https://arxiv.org/pdf/2607.03325)HTML (experimental) (https://arxiv.org/html/2607.03325v1) Abstract:We present an automated pipeline that decomposes Italian tax-court judgments into individual legal issues and extracts, for each issue, a structured XML representation grounded in the IRAC framework and the legal syllogism. The pipeline targets a corpus of approximately 330,000first- and second-instance decisions of the Italian tax courts and is built around a capable yet cost-efficient general-purpose model (DeepSeek V3), a choice driven by the need to process several hundred thousand documents at a sustainable cost. To address the well-documented unreliability of large language models on legal citations, we couple the extraction step with an automatic hallucination-detection filter that compares the references produced by the model with those identified in the judgment text by a dedicated parser (Linkoln), normalised to standard identifiers (URN-NIR, ECLI, CELEX). We validate the pipeline on 50judgments annotated by two PhDs in tax law, computing inter-annotator agreement and LLM-vs-expert agreement on both issue extraction and legal citations, together with a stand-alone evaluation of the hallucination filter. To the best of our knowledge, this is the first issue-level, expert-validated structured extraction pipeline with hallucination control for Italian tax-court decisions, and it provides a concrete starting point for downstream applications such as issue-level retrieval, citation-network analysis, and the construction of large-scale datasets of legal reasoning. Comments:33 pages, 2 figures Subjects:Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR) Cite as:arXiv:2607.03325 (https://arxiv.org/abs/2607.03325) [cs.CL] (or arXiv:2607.03325v1 (https://arxiv.org/abs/2607.03325v1) [cs.CL] for this version) https://doi.org/10.48550/arXiv.2607.03325 arXiv-issued DOI via DataCite (pending registration) Submission history From: Giovanni Piccioli [view email (https://arxiv.org/show-email/b3d06ff7/2607.03325)] • *[v1]** Fri, 3 Jul 2026 13:41:08 UTC (86 KB)