arXiv:2512.11374v1 Announce Type: new 
Abstract: Courts must justify their decisions, but systematically analyzing judicial reasoning at scale remains difficult. This study refutes claims about formalistic judging in Central and Eastern Europe (CEE) by developing automated methods to detect and classify judicial reasoning in Czech Supreme Courts' decisions using state-of-the-art natural language processing methods. We create the MADON dataset of 272 decisions from two Czech Supreme Courts with expert annotations of 9,183 paragraphs with eight argument types and holistic formalism labels for supervised training and evaluation. Using a corpus of 300k Czech court decisions, we adapt transformer LLMs for Czech legal domain by continued pretraining and experiment with methods to address dataset imbalance including asymmetric loss and class weighting. The best models successfully detect argumentative paragraphs (82.6\% macro-F1), classify traditional types of legal argument (77.5\% macro-F1), and classify decisions as formalistic/non-formalistic (83.2\% macro-F1). Our three-stage pipeline combining ModernBERT, Llama 3.1, and traditional feature-based machine learning achieves promising results for decision classification while reducing computational costs and increasing explainability. Empirically, we challenge prevailing narratives about CEE formalism. This work shows that legal argument mining enables reliable judicial philosophy classification and shows the potential of legal argument mining for other important tasks in computational legal studies. Our methodology is easily replicable across jurisdictions, and our entire pipeline, datasets, guidelines, models, and source codes are available at https://github.com/trusthlt/madon.

أظهرت دراسة حديثة تطوير أساليب آلية لتحليل التفكير القضائي في المحاكم العليا التشيكية، مما يتحدى فكرة الحكم الرسمي في أوروبا الوسطى والشرقية. استخدمت الدراسة مجموعة بيانات MADON، التي تتضمن 272 قرارًا وتعليقات خبراء، لتدريب نماذج تصنف الحجج القانونية وتكتشف الفقرات الجدلية بدقة ملحوظة.

Un estudio reciente ha desarrollado métodos automatizados para analizar el razonamiento judicial en las Cortes Supremas checas, desafiando la noción de juicio formalista en Europa Central y del Este. La investigación utilizó el conjunto de datos MADON, que incluye 272 decisiones y anotaciones de expertos, para entrenar modelos que clasifican argumentos legales y detectan párrafos argumentativos con notable precisión.

Une étude récente a développé des méthodes automatisées pour analyser le raisonnement judiciaire dans les Cours suprêmes tchèques, remettant en question la notion de jugement formaliste en Europe centrale et orientale. La recherche a utilisé le jeu de données MADON, qui comprend 272 décisions et des annotations d'experts, pour former des modèles capables de classifier les arguments juridiques et de détecter les paragraphes argumentatifs avec une précision notable.

A recent study has developed automated methods to analyze judicial reasoning in the Czech Supreme Courts, challenging the notion of formalistic judging in Central and Eastern Europe. The research utilized the MADON dataset, which includes 272 decisions and expert annotations, to train models that classify legal arguments and detect argumentative paragraphs with notable accuracy.

Mining Legal Arguments to Study Judicial Formalism

One More Thing in AI – Your Shortcut to AI Mastery

Mining Legal Arguments to Study Judicial Formalism

Was this article worth reading? Share it

One More Thing in AI

LucidQuery AI

MyFramework

Supametas.AI

Sourcely

Meteoria

Ready to build your own newsroom?