Large Language Models in Legislative Content Analysis: A Dataset from the Polish Parliament
Preprint
Abstract
Large language models (LLMs) are among the best methods for processing natural language, partly due to their versatility. At the same time, domain-specific LLMs are more practical in real-life applications. This work introduces a novel natural language dataset created by acquired data from official legislative authorities' websites. The study focuses on formulating three natural language processing (NLP) tasks to evaluate the effectiveness of LLMs on legislative content analysis within the context of the Polish legal system. Key findings highlight the potential of LLMs in automating and enhancing legislative content analysis while emphasizing specific challenges, such as understanding legal context. The research contributes to the advancement of NLP in the legal field, particularly in the Polish language. It has been demonstrated that even commonly accessible data can be practically utilized for legislative content analysis.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Legal Knowledge Representation Learning2023
- LexGLUE: A Benchmark Dataset for Legal Language Understanding in English2022
- MultiEURLEX - A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer2021
- On the Ethical Limits of Natural Language Processing on Legal Text2021
- Pre-training Polish Transformer-Based Language Models at Scale2020
- LEGAL-BERT: The Muppets straight out of Law School2020
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension2020
- KLEJ: Comprehensive Benchmark for Polish Language Understanding2020
- How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligence2020
- Law and Word Order: NLP in Legal TechNatural Language Engineering, 2018