Korean web giant Naver last week debuted a family of large language models called HyperCLOVA X, which it claimed performs better on cross-linguistic reasoning in Asian languages than other models — and could therefore help the region develop superior large language models.
All about Naver's very own AI model 'HyperCLOVA X'
Naver announced the debut of HyperCLOVA X in Korean, pointing to an English-language technical report on open access arXiv that claims "We believe that HyperCLOVA X – with its competitive capabilities in English and languages other than Korean – can provide useful guidance for regions or countries to develop their own superb LLMs."
The LLMs were pretrained on data "consisting of Korean, multilingual and code segments."
The multilingual subset was predominantly English, but also included a variety of other languages – such as Japanese, German and French.
