Researchers have developed an automated pipeline to break down Italian tax court judgments into individual legal issues. This system uses the DeepSeek V3 model to extract structured XML representations grounded in the IRAC framework, aiming for cost-efficiency in processing a large corpus of decisions. A key feature is a hallucination-detection filter that cross-references model-generated legal citations with those found in the judgment text, using tools like Lincoln for parsing and URN-NIR for normalization. The pipeline was validated on 50 judgments annotated by legal experts, demonstrating its potential for applications like issue-level retrieval and dataset construction. AI
IMPACT This research could improve the efficiency and accuracy of legal document analysis and dataset creation for AI systems.
RANK_REASON The cluster contains an academic paper detailing a new methodology for legal text analysis.
Read on arXiv cs.IR (Information Retrieval) →
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
