{"url":"/dataset/cuge","name":"CUGE","full_name":null,"description_markdown":"**CUGE** is a Chinese Language Understanding and Generation Evaluation benchmark with the following features: (1) Hierarchical benchmark framework, where datasets are principally selected and organized with a language capability-task-dataset hierarchy. (2) Multi-level scoring strategy, where different levels of model performance are provided based on the hierarchical framework.\r\n\r\nCUGE covers 7 important language capabilities, 17 mainstream NLP tasks and 19 representative datasets. It includes tasks like: word segmentation, part of speech tagging, reading comprehension and document retrieval.","description_withheld":null,"homepage":"http://cuge.baai.ac.cn/","introduced_date":"2021-12-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/cuge-a-chinese-language-understanding-and","title":"CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark","first_author":"Yuan YAO","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Part-Of-Speech Tagging","url":"/task/part-of-speech-tagging","datasets_with_task":"/datasets/task/part-of-speech-tagging"},{"name":"Chinese Word Segmentation","url":"/task/chinese-word-segmentation","datasets_with_task":"/datasets/task/chinese-word-segmentation"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["CUGE"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"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."}