arxiv: 2404.01954 · v2 · ★pith:LW5NC6OMnew · submitted 2024-04-02 · 💻 cs.CL · cs.AI
HyperCLOVA X Technical Report
show 388 more authors
read the original 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 7 Pith papers
Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.
-
Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web Agents
cs.CL 2026-06 unverdicted novelty 7.0
Ko-WideSearch is a new Korean breadth-search benchmark spanning 16 categories and three difficulty tiers that evaluates web agents on full set membership plus per-item attributes, showing consistent gaps between set r...
-
Anchoring LLM Gender Bias to Human Baselines: A Cross-Lingual Audit
cs.CL 2026-05 unverdicted novelty 6.0
LLM gender stereotyping across four languages spans roughly 2.5 times the human cross-country range on HEXACO-100, with translation altering specific stereotyped attributes and effects that can compound.
-
Discovering Lexical Gaps Using Embeddings from Multilingual LLMs
cs.CL 2026-05 unverdicted novelty 6.0
A framework extracts embeddings from Korean-English bilingual LLMs across thousands of spaces and uses similarity distributions plus logistic classifiers to identify lexical gaps with AUCs of 0.81 and 0.76.
-
K-MetBench: A Multi-Dimensional Benchmark for Fine-Grained Evaluation of Expert Reasoning, Locality, and Multimodality in Meteorology
cs.CL 2026-04 unverdicted novelty 6.0
K-MetBench shows LLMs have large gaps in interpreting meteorology diagrams and Korean-specific context, with smaller local models beating much larger global ones.
-
SCRIPT: A Subcharacter Compositional Representation Injection Module for Korean Pre-Trained Language Models
cs.CL 2026-04 unverdicted novelty 6.0
SCRIPT is a model-agnostic injection module that enhances Korean PLM embeddings with subcharacter compositional knowledge from Jamo, leading to better performance on NLU and NLG tasks and more linguistically coherent ...
-
CHERRY: Compressed Hierarchical Experts with Recurrent Representational Yield
cs.CL 2026-06 unverdicted novelty 5.0
CHERRY combines selective ground-truth token training, recurrent depth compression from 48 to 6 layers, and mixture-of-efficient-experts to achieve competitive loss with fewer parameters on a 1.8B Korean model.
-
SemEval-2026 Task 7: Everyday Knowledge Across Diverse Languages and Cultures
cs.CL 2026-05 unverdicted novelty 4.0
SemEval-2026 Task 7 presents a benchmark and two evaluation tracks for assessing LLMs on everyday knowledge in diverse languages and cultures without allowing training on the test data.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.