Construction of a Japanese Financial Benchmark for Large Language Models

TL;DR

A benchmark comprising multiple tasks specific to the Japanese and financial domains and performed benchmark measurements on some models confirmed that GPT-4 is currently outstanding, and that the constructed benchmarks function effectively.

Abstract

With the recent development of large language models (LLMs), models that focus on certain domains and languages have been discussed for their necessity. There is also a growing need for benchmarks to evaluate the performance of current LLMs in each domain. Therefore, in this study, we constructed a benchmark comprising multiple tasks specific to the Japanese and financial domains and performed benchmark measurements on some models. Consequently, we confirmed that GPT-4 is currently outstanding, and that the constructed benchmarks function effectively. According to our analysis, our benchmark can differentiate benchmark scores among models in all performance ranges by combining tasks with different difficulties.

Figures (5)

• Figure 1: Relationship between Benchmark and chabsa scores
• Figure 2: Relationship between Benchmark and cma_basics scores
• Figure 3: Relationship between Benchmark and cpa_audit scores
• Figure 4: Relationship between Benchmark and fp2 scores
• Figure 5: Relationship between Benchmark and security_sales_1 scores