Making Sense of Korean Sentences: A Comprehensive Evaluation of LLMs through KoSEnd Dataset
This addresses the challenge of LLM performance in Korean for NLP researchers, but it is incremental as it primarily evaluates existing models on a new dataset.
The study tackled the problem of evaluating LLMs' effectiveness with low-resource agglutinative languages like Korean, focusing on complex sentence endings, and found that informing models about missing endings improved performance.
Although LLMs have made significant progress in various languages, there are still concerns about their effectiveness with low-resource agglutinative languages compared to languages such as English. In this study, we focused on Korean, a language known for its complex sentence endings, and evaluated LLMs on this challenging aspect. We introduce the Korean Sentence Endings (KoSEnd) dataset, which includes 3,000 sentences, each annotated for the naturalness of 15 sentence ending forms. These were collected from diverse sources to cover a range of contexts. We evaluated 11 LLMs to assess their understanding of Korean sentence endings, analyzing them based on parameter count and prediction consistency. Notably, we found that informing models about the possibility of missing sentence endings improved performance, highlighting the impact of explicitly considering certain linguistic features.