增强法律文档检索：一种基于大型语言模型的多阶段方法
Enhancing Legal Document Retrieval: A Multi-Phase Approach with Large Language Models
AI总结：
本研究提出一种结合 BM25 预排序、基于 BERT 的重排序与 LLM 提示技术的多阶段法律文档检索方法，在 COLIEE 2023 数据集上显著提升了检索准确率。
摘要：
具有数十亿参数的大型语言模型，如 GPT-3.5、GPT-4 和 LLaMA，日益普及。许多研究探索了有效的提示技术，以利用这些 LLM 的能力来解决各种研究问题。检索，特别是在法律数据领域，由于法律条文数量庞大且篇幅冗长，对提示技术的直接应用构成了挑战。本研究专注于最大化提示技术的潜力，将其作为检索系统的最终阶段，在此之前由两个阶段提供支持：BM25 预排序和基于 BERT 的重排序。在 COLIEE 2023 数据集上的实验表明，将 LLM 上的提示技术集成到检索系统中可显著提高检索准确率。然而，错误分析揭示了检索系统中仍存在若干需要解决的问题。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
