Name: yangzhang33/culture-eval-benchmark-cs-filtered
Creator: yangzhang33
Published: 2026-04-01 12:43:53
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/yangzhang33/culture-eval-benchmark-cs-filtered

下载链接

链接失效反馈

官方服务：

资源简介：

--- dataset_info: - config_name: arabic_ca features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool - name: CEB_index dtype: int64 - name: CEB_config dtype: string splits: - name: test num_bytes: 1457478 num_examples: 2058 download_size: 584462 dataset_size: 1457478 - config_name: arabic_cs features: - name: ID dtype: int64 - name: Source dtype: string - name: Country dtype: string - name: Group dtype: string - name: Subject dtype: string - name: Level dtype: string - name: Context dtype: string - name: is_few_shot dtype: int64 - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: config dtype: string - name: CEB_index dtype: int64 - name: CEB_config dtype: string - name: claude_cs dtype: int64 splits: - name: test num_bytes: 2685598.6726618707 num_examples: 3591 download_size: 518614 dataset_size: 2685598.6726618707 - config_name: chinese_ca features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool - name: CEB_index dtype: int64 - name: CEB_config dtype: string splits: - name: test num_bytes: 1019008 num_examples: 2058 download_size: 455948 dataset_size: 1019008 - config_name: chinese_cs features: - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: config dtype: string - name: CEB_index dtype: int64 - name: CEB_config dtype: string - name: claude_cs dtype: int64 splits: - name: test num_bytes: 467853.0507529281 num_examples: 1460 download_size: 290957 dataset_size: 467853.0507529281 - config_name: english_ca features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool - name: CEB_index dtype: int64 - name: CEB_config dtype: string splits: - name: test num_bytes: 1137402 num_examples: 2058 download_size: 487286 dataset_size: 1137402 - config_name: greek_ca features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool - name: CEB_index dtype: int64 - name: CEB_config dtype: string splits: - name: test num_bytes: 1784881 num_examples: 2058 download_size: 720588 dataset_size: 1784881 - config_name: greek_cs features: - name: question dtype: string - name: answer dtype: string - name: group dtype: string - name: subject dtype: string - name: level dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: config dtype: string - name: CEB_index dtype: int64 - name: CEB_config dtype: string - name: claude_cs dtype: int64 splits: - name: test num_bytes: 347768.4934277047 num_examples: 785 download_size: 139195 dataset_size: 347768.4934277047 - config_name: hindi_ca features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool - name: CEB_index dtype: int64 - name: CEB_config dtype: string splits: - name: test num_bytes: 2106295 num_examples: 2058 download_size: 712842 dataset_size: 2106295 - config_name: hindi_cs features: - name: question dtype: string - name: is_translated dtype: bool - name: language dtype: string - name: subject dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: config dtype: string - name: CEB_index dtype: int64 - name: CEB_config dtype: string - name: claude_cs dtype: int64 splits: - name: test num_bytes: 2177945.123658423 num_examples: 4360 download_size: 803776 dataset_size: 2177945.123658423 - config_name: indonesian_ca features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool - name: CEB_index dtype: int64 - name: CEB_config dtype: string splits: - name: test num_bytes: 1176983 num_examples: 2058 download_size: 483575 dataset_size: 1176983 - config_name: indonesian_cs features: - name: group dtype: string - name: level dtype: string - name: class dtype: string - name: question dtype: string - name: answer dtype: string - name: is_for_fewshot dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: config dtype: string - name: CEB_index dtype: int64 - name: CEB_config dtype: string - name: claude_cs dtype: int64 splits: - name: test num_bytes: 670161.8436965202 num_examples: 1634 download_size: 303373 dataset_size: 670161.8436965202 - config_name: korean_ca features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool - name: CEB_index dtype: int64 - name: CEB_config dtype: string splits: - name: test num_bytes: 1209729 num_examples: 2058 download_size: 519101 dataset_size: 1209729 - config_name: korean_cs features: - name: question dtype: string - name: answer dtype: string - name: Category dtype: string - name: Human Accuracy dtype: float64 - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: config dtype: string - name: CEB_index dtype: int64 - name: CEB_config dtype: string - name: claude_cs dtype: int64 splits: - name: test num_bytes: 1161852.2923880597 num_examples: 2543 download_size: 776466 dataset_size: 1161852.2923880597 configs: - config_name: arabic_ca data_files: - split: test path: arabic_ca/test-* - config_name: arabic_cs data_files: - split: test path: arabic_cs/test-* - config_name: chinese_ca data_files: - split: test path: chinese_ca/test-* - config_name: chinese_cs data_files: - split: test path: chinese_cs/test-* - config_name: english_ca data_files: - split: test path: english_ca/test-* - config_name: greek_ca data_files: - split: test path: greek_ca/test-* - config_name: greek_cs data_files: - split: test path: greek_cs/test-* - config_name: hindi_ca data_files: - split: test path: hindi_ca/test-* - config_name: hindi_cs data_files: - split: test path: hindi_cs/test-* - config_name: indonesian_ca data_files: - split: test path: indonesian_ca/test-* - config_name: indonesian_cs data_files: - split: test path: indonesian_cs/test-* - config_name: korean_ca data_files: - split: test path: korean_ca/test-* - config_name: korean_cs data_files: - split: test path: korean_cs/test-* ---

应用场景：