Developing a Pragmatic Benchmark for Assessing Korean Legal Language Understanding in Large Language Models
This addresses the need for domain-specific evaluation of LLMs in non-English legal systems, but it is incremental as it adapts existing benchmarking approaches to a new language and domain.
The authors tackled the problem of evaluating large language models (LLMs) for Korean legal language understanding by introducing the KBL benchmark, which includes legal knowledge, reasoning tasks, and the Korean bar exam, and found substantial room for improvement in LLM performance.
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.