{"url":"/dataset/klue","name":"KLUE","full_name":"Korean Language Understanding Evaluation","description_markdown":"Korean Language Understanding Evaluation (**KLUE**) benchmark is a series of datasets to evaluate natural language understanding capability of Korean language models. KLUE consists of 8 diverse and representative tasks, which are accessible to anyone without any restrictions. With ethical considerations in mind, we deliberately design annotation guidelines to obtain unambiguous annotations for all datasets. Furthermore, we build an evaluation system and carefully choose evaluations metrics for every task, thus establishing fair comparison across Korean language models.\r\n\r\nKLUE benchmark is composed of 8 tasks:\r\n\r\n- Topic Classification (TC)\r\n- Sentence Textual Similarity (STS)\r\n- Natural Language Inference (NLI)\r\n- Named Entity Recognition (NER)\r\n- Relation Extraction (RE)\r\n- (Part-Of-Speech) + Dependency Parsing (DP)\r\n- Machine Reading Comprehension (MRC)\r\n- Dialogue State Tracking (DST)","description_withheld":null,"homepage":"https://klue-benchmark.com/","introduced_date":"2021-05-20","introduced_date_note":null,"introduced_by":{"paper":"/paper/klue-korean-language-understanding-evaluation","title":"KLUE: Korean Language Understanding Evaluation","first_author":"Sungjoon Park","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"Relation Extraction","url":"/task/relation-extraction","datasets_with_task":"/datasets/task/relation-extraction"},{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"},{"name":"Dependency Parsing","url":"/task/dependency-parsing","datasets_with_task":"/datasets/task/dependency-parsing"},{"name":"Dialogue State Tracking","url":"/task/dialogue-state-tracking","datasets_with_task":"/datasets/task/dialogue-state-tracking"},{"name":"Machine Reading Comprehension","url":"/task/machine-reading-comprehension","datasets_with_task":"/datasets/task/machine-reading-comprehension"},{"name":"Topic Classification","url":"/task/topic-classification","datasets_with_task":"/datasets/task/topic-classification"}],"languages":[{"name":"Korean","url":"/datasets/language/korean"}],"variants":["KLUE"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/klue/klue","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/min9805/skb","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/klue","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":21,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-classification-on-klue","task":"Text Classification","dataset_variant":"KLUE","rows":0,"metrics":["Accuracy","F1","Pearsonr"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}