Developing a Pragmatic Benchmark for Assessing Korean Legal Language Understanding in Large Language Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kim, Yeeun, Choi, Young Rok, Choi, Eunkyung, Choi, Jinhwan, Park, Hai Jin, Hwang, Wonseok
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912069229477888
author Kim, Yeeun
Choi, Young Rok
Choi, Eunkyung
Choi, Jinhwan
Park, Hai Jin
Hwang, Wonseok
author_facet Kim, Yeeun
Choi, Young Rok
Choi, Eunkyung
Choi, Jinhwan
Park, Hai Jin
Hwang, Wonseok
contents Large language models (LLMs) have demonstrated remarkable performance in the legal domain, with GPT-4 even passing the Uniform Bar Exam in the U.S. However their efficacy remains limited for non-standardized tasks and tasks in languages other than English. This underscores the need for careful evaluation of LLMs within each legal system before application. Here, we introduce KBL, a benchmark for assessing the Korean legal language understanding of LLMs, consisting of (1) 7 legal knowledge tasks (510 examples), (2) 4 legal reasoning tasks (288 examples), and (3) the Korean bar exam (4 domains, 53 tasks, 2,510 examples). First two datasets were developed in close collaboration with lawyers to evaluate LLMs in practical scenarios in a certified manner. Furthermore, considering legal practitioners' frequent use of extensive legal documents for research, we assess LLMs in both a closed book setting, where they rely solely on internal knowledge, and a retrieval-augmented generation (RAG) setting, using a corpus of Korean statutes and precedents. The results indicate substantial room and opportunities for improvement.
format Preprint
id arxiv_https___arxiv_org_abs_2410_08731
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Developing a Pragmatic Benchmark for Assessing Korean Legal Language Understanding in Large Language Models
Kim, Yeeun
Choi, Young Rok
Choi, Eunkyung
Choi, Jinhwan
Park, Hai Jin
Hwang, Wonseok
Computation and Language
Artificial Intelligence
Large language models (LLMs) have demonstrated remarkable performance in the legal domain, with GPT-4 even passing the Uniform Bar Exam in the U.S. However their efficacy remains limited for non-standardized tasks and tasks in languages other than English. This underscores the need for careful evaluation of LLMs within each legal system before application. Here, we introduce KBL, a benchmark for assessing the Korean legal language understanding of LLMs, consisting of (1) 7 legal knowledge tasks (510 examples), (2) 4 legal reasoning tasks (288 examples), and (3) the Korean bar exam (4 domains, 53 tasks, 2,510 examples). First two datasets were developed in close collaboration with lawyers to evaluate LLMs in practical scenarios in a certified manner. Furthermore, considering legal practitioners' frequent use of extensive legal documents for research, we assess LLMs in both a closed book setting, where they rely solely on internal knowledge, and a retrieval-augmented generation (RAG) setting, using a corpus of Korean statutes and precedents. The results indicate substantial room and opportunities for improvement.
title Developing a Pragmatic Benchmark for Assessing Korean Legal Language Understanding in Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2410.08731