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

Date

2026

Author

Erkan, Mehmet Ali
Yozgatlıgil, Ceylan

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Item Usage Stats

465
views

31
downloads

Cite This

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.

Subject Keywords

Turkish Legal NLP, Benchmark Dataset, Multi-Task Learning, Text Classification, Legal Reasoning, Low-Resource Languages

URI

https://doi.org/10.5281/zenodo.18555735
https://hdl.handle.net/11511/118433

Collections

Department of Statistics, Research data