TurkishLegalBench: A Comprehensive Multi-Task Benchmark Suite for Turkish Legal NLP

Creative Commons License

Erkan M. A., Yozgatlıgil C.

  • Yayınlanma Tarihi: 12 Şubat 2026
  • Versiyon: 1
  • Üniversite / Kurum: Orta Doğu Teknik Üniversitesi
  • Araştırma Alanı: Bilgisayar Bilimleri , Veritabanı ve Veri Yapıları , Veri Gösterimi ve Saklanması , Mühendislik ve Teknoloji

Açıklama


Description

TurkishLegalBench is a large-scale, multi-task benchmark suite specifically designed for Natural Language Processing (NLP) in the Turkish legal domain. The dataset consists of 38,009 authentic legal documents curated from Turkish high courts. It covers seven distinct legal tasks categorized under three pillars: Classification (TurkVerdict, TurkVenue, TurkCanon), Extraction (TurkChronos, TurkCite), and Reasoning (TurkCoherence, TurkAudit). This resource aims to bridge the gap in low-resource legal NLP for Turkish and provides a standardized evaluation framework for researchers.


Description

TurkishLegalBench is a large-scale, multi-task benchmark suite specifically designed for Natural Language Processing (NLP) in the Turkish legal domain. The dataset consists of 38,009 authentic legal documents curated from Turkish high courts. It covers seven distinct legal tasks categorized under three pillars: Classification (TurkVerdict, TurkVenue, TurkCanon), Extraction (TurkChronos, TurkCite), and Reasoning (TurkCoherence, TurkAudit). This resource aims to bridge the gap in low-resource legal NLP for Turkish and provides a standardized evaluation framework for researchers.

BM Sürdürülebilir Kalkınma Amaçları
Paylaş