# From Judgments to Issues: Structured Extraction of Legal Reasoning with Citation-Hallucination Control

arXiv: https://arxiv.org/abs/2607.03325 · HTML: https://mlsanity.com/paper/2607.03325/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 13 of its 70 references that are in the map.
- First posted on arXiv 3 Jul 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 13 of 13)

- [Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models](https://mlsanity.com/paper/2401.01301/) (2024)
- [Legal Prompting: Teaching a Language Model to Think Like a Lawyer](https://mlsanity.com/paper/2212.01326/) (2022)
- [Legal Syllogism Prompting: Teaching Large Language Models for Legal Judgment Prediction](https://mlsanity.com/paper/2307.08321/) (2023)
- [Mining Legal Arguments in Court Decisions](https://mlsanity.com/paper/2208.06178/) (2022)
- [LLMs Provide Unstable Answers to Legal Questions](https://mlsanity.com/paper/2502.05196/) (2025)
- [Measuring Law Over Time: A Network Analytical Framework with an Application to Statutes and Regulations in the United States and Germany](https://mlsanity.com/paper/2101.11284/) (2021)
- [From Text to Structure: Using Large Language Models to Support the Development of Legal Expert Systems](https://mlsanity.com/paper/2311.04911/) (2023)
- [Evaluating AI for Law: Bridging the Gap with Open-Source Solutions](https://mlsanity.com/paper/2404.12349/) (2024)
- [Legal Summarisation through LLMs: The PRODIGIT Project](https://mlsanity.com/paper/2308.04416/) (2023)
- [Harnessing GPT-3.5-turbo for Rhetorical Role Prediction in Legal Cases](https://mlsanity.com/paper/2310.17413/) (2023)
- [Question-Answering Approach to Evaluating Legal Summaries](https://mlsanity.com/paper/2309.15016/) (2023)
- [Automating IRAC Analysis in Malaysian Contract Law using a Semi-Structured Knowledge Base](https://mlsanity.com/paper/2406.13217/) (2024)
- [Identifying Legal Holdings with LLMs: A Systematic Study of Performance, Scale, and Memorization](https://mlsanity.com/paper/2505.02172/) (2025)

## Abstract (arXiv)

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 330,000 first- 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 50 judgments 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.