Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.00725 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915222198943744 |
|---|---|
| author | Belarmino, Matheus Coelho, Rackel Lotudo, Roberto Pereira, Jayr |
| author_facet | Belarmino, Matheus Coelho, Rackel Lotudo, Roberto Pereira, Jayr |
| contents | Large Language Models (LLMs) have been increasingly used to optimize the analysis and synthesis of legal documents, enabling the automation of tasks such as summarization, classification, and retrieval of legal information. This study aims to conduct a systematic literature review to identify the state of the art in prompt engineering applied to LLMs in the legal context. The results indicate that models such as GPT-4, BERT, Llama 2, and Legal-Pegasus are widely employed in the legal field, and techniques such as Few-shot Learning, Zero-shot Learning, and Chain-of-Thought prompting have proven effective in improving the interpretation of legal texts. However, challenges such as biases in models and hallucinations still hinder their large-scale implementation. It is concluded that, despite the great potential of LLMs for the legal field, there is a need to improve prompt engineering strategies to ensure greater accuracy and reliability in the generated results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_00725 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Aplicação de Large Language Models na Análise e Síntese de Documentos Jurídicos: Uma Revisão de Literatura Belarmino, Matheus Coelho, Rackel Lotudo, Roberto Pereira, Jayr Computation and Language Large Language Models (LLMs) have been increasingly used to optimize the analysis and synthesis of legal documents, enabling the automation of tasks such as summarization, classification, and retrieval of legal information. This study aims to conduct a systematic literature review to identify the state of the art in prompt engineering applied to LLMs in the legal context. The results indicate that models such as GPT-4, BERT, Llama 2, and Legal-Pegasus are widely employed in the legal field, and techniques such as Few-shot Learning, Zero-shot Learning, and Chain-of-Thought prompting have proven effective in improving the interpretation of legal texts. However, challenges such as biases in models and hallucinations still hinder their large-scale implementation. It is concluded that, despite the great potential of LLMs for the legal field, there is a need to improve prompt engineering strategies to ensure greater accuracy and reliability in the generated results. |
| title | Aplicação de Large Language Models na Análise e Síntese de Documentos Jurídicos: Uma Revisão de Literatura |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.00725 |