HyperCLOVA X Technical Report

TL;DR

HyperCLOVA X is a large language model tailored for Korean and capable in English, math, and coding, trained on multilingual data, and evaluated across diverse benchmarks demonstrating strong reasoning and cross-lingual abilities.

Contribution

The paper introduces HyperCLOVA X, a multilingual LLM with a focus on Korean, highlighting its training process, safety measures, and extensive evaluation across various tasks and languages.

Findings

Strong reasoning and cultural understanding in Korean.

Effective cross-lingual and multilingual generalization.

High performance on diverse benchmarks.

Abstract

We introduce HyperCLOVA X, a family of large language models (LLMs) tailored to the Korean language and culture, along with competitive capabilities in English, math, and coding. HyperCLOVA X was trained on a balanced mix of Korean, English, and code data, followed by instruction-tuning with high-quality human-annotated datasets while abiding by strict safety guidelines reflecting our commitment to responsible AI. The model is evaluated across various benchmarks, including comprehensive reasoning, knowledge, commonsense, factuality, coding, math, chatting, instruction-following, and harmlessness, in both Korean and English. HyperCLOVA X exhibits strong reasoning capabilities in Korean backed by a deep understanding of the language and cultural nuances. Further analysis of the inherent bilingual nature and its extension to multilingualism highlights the model's cross-lingual proficiency and strong generalization ability to untargeted languages, including machine translation between several language pairs and cross-lingual inference tasks. We believe that HyperCLOVA X can provide helpful guidance for regions or countries in developing their sovereign LLMs.