KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge

TL;DR

KorNAT is a comprehensive benchmark designed to evaluate Korean-specific social values and knowledge in large language models, highlighting the need for culturally aligned AI systems.

Contribution

This paper introduces KorNAT, the first benchmark for assessing LLMs' understanding of Korean social values and knowledge, with a rigorous dataset creation process and government approval.

Findings

Few models meet the reference scores, indicating room for improvement.

The benchmark reveals significant gaps in current LLMs' cultural understanding.

KorNAT provides a standardized evaluation protocol for Korean LLM alignment.

Abstract

For Large Language Models (LLMs) to be effectively deployed in a specific country, they must possess an understanding of the nation's culture and basic knowledge. To this end, we introduce National Alignment, which measures an alignment between an LLM and a targeted country from two aspects: social value alignment and common knowledge alignment. Social value alignment evaluates how well the model understands nation-specific social values, while common knowledge alignment examines how well the model captures basic knowledge related to the nation. We constructed KorNAT, the first benchmark that measures national alignment with South Korea. For the social value dataset, we obtained ground truth labels from a large-scale survey involving 6,174 unique Korean participants. For the common knowledge dataset, we constructed samples based on Korean textbooks and GED reference materials. KorNAT contains 4K and 6K multiple-choice questions for social value and common knowledge, respectively. Our dataset creation process is meticulously designed and based on statistical sampling theory and was refined through multiple rounds of human review. The experiment results of seven LLMs reveal that only a few models met our reference score, indicating a potential for further enhancement. KorNAT has received government approval after passing an assessment conducted by a government-affiliated organization dedicated to evaluating dataset quality. Samples and detailed evaluation protocols of our dataset can be found in https://huggingface.co/datasets/jiyounglee0523/KorNAT .