Enhancing Legal Document Retrieval: A Multi-Phase Approach with Large Language Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914730221764608 |
|---|---|
| author | Nguyen, Hai-Long Nguyen, Duc-Minh Nguyen, Tan-Minh Nguyen, Ha-Thanh Vuong, Thi-Hai-Yen Satoh, Ken |
| author_facet | Nguyen, Hai-Long Nguyen, Duc-Minh Nguyen, Tan-Minh Nguyen, Ha-Thanh Vuong, Thi-Hai-Yen Satoh, Ken |
| contents | Large language models with billions of parameters, such as GPT-3.5, GPT-4, and LLaMA, are increasingly prevalent. Numerous studies have explored effective prompting techniques to harness the power of these LLMs for various research problems. Retrieval, specifically in the legal data domain, poses a challenging task for the direct application of Prompting techniques due to the large number and substantial length of legal articles. This research focuses on maximizing the potential of prompting by placing it as the final phase of the retrieval system, preceded by the support of two phases: BM25 Pre-ranking and BERT-based Re-ranking. Experiments on the COLIEE 2023 dataset demonstrate that integrating prompting techniques on LLMs into the retrieval system significantly improves retrieval accuracy. However, error analysis reveals several existing issues in the retrieval system that still need resolution. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_18093 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Legal Document Retrieval: A Multi-Phase Approach with Large Language Models Nguyen, Hai-Long Nguyen, Duc-Minh Nguyen, Tan-Minh Nguyen, Ha-Thanh Vuong, Thi-Hai-Yen Satoh, Ken Computation and Language Artificial Intelligence Large language models with billions of parameters, such as GPT-3.5, GPT-4, and LLaMA, are increasingly prevalent. Numerous studies have explored effective prompting techniques to harness the power of these LLMs for various research problems. Retrieval, specifically in the legal data domain, poses a challenging task for the direct application of Prompting techniques due to the large number and substantial length of legal articles. This research focuses on maximizing the potential of prompting by placing it as the final phase of the retrieval system, preceded by the support of two phases: BM25 Pre-ranking and BERT-based Re-ranking. Experiments on the COLIEE 2023 dataset demonstrate that integrating prompting techniques on LLMs into the retrieval system significantly improves retrieval accuracy. However, error analysis reveals several existing issues in the retrieval system that still need resolution. |
| title | Enhancing Legal Document Retrieval: A Multi-Phase Approach with Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2403.18093 |