Nearest Neighbor Search for Summarization of Japanese Judgment Documents

被引：0

作者：

Shimbo, Akito ^{[1
]}

Sugawara, Yuta ^{[1
]}

Yamada, Hiroaki ^{[1
]}

Tokunaga, Takenobu ^{[1
]}

机构：

[1] Tokyo Inst Technol, Tokyo, Japan

来源：

LEGAL KNOWLEDGE AND INFORMATION SYSTEMS | 2023年 / 379卷

关键词：

summarization; large language model; nearest neighbor search; Japanese judgment document;

D O I：

10.3233/FAIA230984

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

With the increasing demand for summarizing Japanese judgment documents, the automatic generation of high-quality summaries by large language models (LLMs) is expected. We propose a method to select exemplars using the nearest neighbor search for the one-shot learning method. The experiments showed our method outperforms baseline methods.

引用

页码：335 / 340

页数：6