LEGAL-UQA: A Low-Resource Urdu-English Dataset for Legal Question Answering

TL;DR

LEGAL-UQA is a novel Urdu-English legal question-answering dataset derived from Pakistan's constitution, enabling NLP research in low-resource languages and specialized legal domains.

Contribution

The paper introduces the first Urdu legal QA dataset, detailing its creation, and evaluates state-of-the-art models, highlighting challenges and performance in low-resource legal NLP tasks.

Findings

Claude-3.5-Sonnet achieves 99.19% accuracy on LEGAL-UQA.

OpenAI's text-embedding-3-large outperforms Mistral's embed in retrieval tasks.

Fine-tuning multilingual models like mt5-large-UQA-1.0 reveals domain adaptation challenges.

Abstract

We present LEGAL-UQA, the first Urdu legal question-answering dataset derived from Pakistan's constitution. This parallel English-Urdu dataset includes 619 question-answer pairs, each with corresponding legal article contexts, addressing the need for domain-specific NLP resources in low-resource languages. We describe the dataset creation process, including OCR extraction, manual refinement, and GPT-4-assisted translation and generation of QA pairs. Our experiments evaluate the latest generalist language and embedding models on LEGAL-UQA, with Claude-3.5-Sonnet achieving 99.19% human-evaluated accuracy. We fine-tune mt5-large-UQA-1.0, highlighting the challenges of adapting multilingual models to specialized domains. Additionally, we assess retrieval performance, finding OpenAI's text-embedding-3-large outperforms Mistral's mistral-embed. LEGAL-UQA bridges the gap between global NLP advancements and localized applications, particularly in constitutional law, and lays the foundation for improved legal information access in Pakistan.