{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/cblue-a-chinese-biomedical-language","title":"CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark","arxiv_id":"2106.08087","date":"2021-06-15","proceeding":"ACL 2022 5","authors":["Ningyu Zhang","Mosha Chen","Zhen Bi","Xiaozhuan Liang","Lei LI","Xin Shang","Kangping Yin","Chuanqi Tan","Jian Xu","Fei Huang","Luo Si","Yuan Ni","Guotong Xie","Zhifang Sui","Baobao Chang","Hui Zong","Zheng Yuan","Linfeng Li","Jun Yan","Hongying Zan","Kunli Zhang","Buzhou Tang","Qingcai Chen"],"abstract":"Artificial Intelligence (AI), along with the recent progress in biomedical language understanding, is gradually changing medical practice. With the development of biomedical language understanding benchmarks, AI applications are widely used in the medical field. However, most benchmarks are limited to English, which makes it challenging to replicate many of the successes in English for other languages. To facilitate research in this direction, we collect real-world biomedical data and present the first Chinese Biomedical Language Understanding Evaluation (CBLUE) benchmark: a collection of natural language understanding tasks including named entity recognition, information extraction, clinical diagnosis normalization, single-sentence/sentence-pair classification, and an associated online platform for model evaluation, comparison, and analysis. To establish evaluation on these tasks, we report empirical results with the current 11 pre-trained Chinese models, and experimental results show that state-of-the-art neural models perform by far worse than the human ceiling. Our benchmark is released at \\url{https://tianchi.aliyun.com/dataset/dataDetail?dataId=95414&lang=en-us}.","url_abs":"https://arxiv.org/abs/2106.08087v6","url_pdf":"https://arxiv.org/pdf/2106.08087v6.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"cblue-a-chinese-biomedical-language","repo_url":"https://github.com/cbluebenchmark/cblue","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"cblue-a-chinese-biomedical-language","repo_url":"https://github.com/freedomintelligence/sdak","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"intent-classification","task_name":"Intent Classification"},{"task_slug":"medical-concept-normalization","task_name":"Medical Concept Normalization"},{"task_slug":"medical-relation-extraction","task_name":"Medical Relation Extraction"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-classification","task_name":"Sentence Classification"},{"task_slug":"sentence-pair-classification","task_name":"Sentence-Pair Classification"}],"methods":[{"method_slug":"albert","method_name":"ALBERT"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"roberta","method_name":"RoBERTa"}],"datasets_introduced":[{"slug":"chip-cdn","name":"CHIP-CDN","full_name":"Clinical Diagnosis Normalization Dataset"},{"slug":"chip-sts","name":"CHIP-STS","full_name":"Semantic Textual Similarity Dataset"},{"slug":"cmeee","name":"CMeEE","full_name":"Chinese Medical Named Entity Recognition Dataset"},{"slug":"kuake-qic","name":"KUAKE-QIC","full_name":"Query Intent Classification Dataset"},{"slug":"kuake-qqr","name":"KUAKE-QQR","full_name":"Query-Query Relevance Dataset"},{"slug":"kuake-qtr","name":"KUAKE-QTR","full_name":"Query-Title Relevance Dataset"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/intent-classification-on-kuake-qic","task":"Intent Classification","dataset":"KUAKE-QIC","model":"RoBERTa-wwm-ext-base","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"85.5"},"uses_additional_data":false},{"leaderboard":"/sota/medical-relation-extraction-on-cmeie","task":"Medical Relation Extraction","dataset":"CMeIE","model":"RoBERTa-wwm-ext-large","rank_in_archive_order":1,"of":1,"metrics":{"Micro F1":"55.9"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-on-cmeee","task":"Named Entity Recognition (NER)","dataset":"CMeEE","model":"MacBERT-large","rank_in_archive_order":2,"of":2,"metrics":{"Micro F1":"62.4"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-kuake-qqr","task":"Natural Language Inference","dataset":"KUAKE-QQR","model":"BERT-base","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"84.7"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-kuake-qtr","task":"Natural Language Inference","dataset":"KUAKE-QTR","model":"MacBERT-large","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"62.9"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-similarity-on-chip-sts","task":"Semantic Similarity","dataset":"CHIP-STS","model":"MacBERT-large","rank_in_archive_order":1,"of":1,"metrics":{"Macro F1":"85.6"},"uses_additional_data":false},{"leaderboard":"/sota/sentence-classification-on-chip-ctc","task":"Sentence Classification","dataset":"CHIP-CTC","model":"RoBERTa-large","rank_in_archive_order":1,"of":1,"metrics":{"Macro F1":"70.9"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.08087","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08087"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cbluebenchmark/cblue","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/freedomintelligence/sdak","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":3,"ran_honours":1,"unverified":12},"by_repo_kind":{"official":{"samples":16,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"cf9ffa02a42184af","entry":"whitespace_tokenize","repo":"cbluebenchmark/cblue","repo_kind":"official","path":"cblue/models/zen/tokenization.py","file_url":"https://github.com/cbluebenchmark/cblue/blob/HEAD/cblue/models/zen/tokenization.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"code_sha256_prefix":"fdc64f4c72036ae4","entry":"gelu","repo":"cbluebenchmark/cblue","repo_kind":"official","path":"cblue/models/zen/modeling.py","file_url":"https://github.com/cbluebenchmark/cblue/blob/HEAD/cblue/models/zen/modeling.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"code_sha256_prefix":"d30d6c3098df2c42","entry":"prune_linear_layer","repo":"cbluebenchmark/cblue","repo_kind":"official","path":"cblue/models/zen/modeling.py","file_url":"https://github.com/cbluebenchmark/cblue/blob/HEAD/cblue/models/zen/modeling.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"code_sha256_prefix":"5eff22fa0a651276","entry":"url_to_filename","repo":"cbluebenchmark/cblue","repo_kind":"official","path":"cblue/models/zen/file_utils.py","file_url":"https://github.com/cbluebenchmark/cblue/blob/HEAD/cblue/models/zen/file_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5eff22fa0a651276"}},{"code_sha256_prefix":"cf9c448c96f48428","entry":"cached_path","repo":"cbluebenchmark/cblue","repo_kind":"official","path":"cblue/models/zen/file_utils.py","file_url":"https://github.com/cbluebenchmark/cblue/blob/HEAD/cblue/models/zen/file_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cf9c448c96f48428"}},{"code_sha256_prefix":"d77c1cad6b941ff2","entry":"convert_examples_to_features","repo":"cbluebenchmark/cblue","repo_kind":"official","path":"cblue/models/zen/data.py","file_url":"https://github.com/cbluebenchmark/cblue/blob/HEAD/cblue/models/zen/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d77c1cad6b941ff2"}},{"code_sha256_prefix":"081479ed6ae40f0d","entry":"convert_examples_to_features_for_tokens","repo":"cbluebenchmark/cblue","repo_kind":"official","path":"cblue/models/zen/data.py","file_url":"https://github.com/cbluebenchmark/cblue/blob/HEAD/cblue/models/zen/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"081479ed6ae40f0d"}},{"code_sha256_prefix":"0dd59e7198cafb75","entry":"ctc_metric","repo":"cbluebenchmark/cblue","repo_kind":"official","path":"cblue/metrics/cblue_metrics.py","file_url":"https://github.com/cbluebenchmark/cblue/blob/HEAD/cblue/metrics/cblue_metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0dd59e7198cafb75"}},{"code_sha256_prefix":"f7aa06f500546846","entry":"ee_metric","repo":"cbluebenchmark/cblue","repo_kind":"official","path":"cblue/metrics/cblue_metrics.py","file_url":"https://github.com/cbluebenchmark/cblue/blob/HEAD/cblue/metrics/cblue_metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f7aa06f500546846"}},{"code_sha256_prefix":"a6aab787fcf8b10d","entry":"filename_to_url","repo":"cbluebenchmark/cblue","repo_kind":"official","path":"cblue/models/zen/file_utils.py","file_url":"https://github.com/cbluebenchmark/cblue/blob/HEAD/cblue/models/zen/file_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a6aab787fcf8b10d"}},{"code_sha256_prefix":"b26659d849aa4a63","entry":"load_dict","repo":"cbluebenchmark/cblue","repo_kind":"official","path":"cblue/utils.py","file_url":"https://github.com/cbluebenchmark/cblue/blob/HEAD/cblue/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b26659d849aa4a63"}},{"code_sha256_prefix":"e02b2a940d01312d","entry":"load_json","repo":"cbluebenchmark/cblue","repo_kind":"official","path":"cblue/utils.py","file_url":"https://github.com/cbluebenchmark/cblue/blob/HEAD/cblue/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e02b2a940d01312d"}},{"code_sha256_prefix":"b1a7180868dd8d6a","entry":"load_tf_weights_in_bert","repo":"cbluebenchmark/cblue","repo_kind":"official","path":"cblue/models/zen/modeling.py","file_url":"https://github.com/cbluebenchmark/cblue/blob/HEAD/cblue/models/zen/modeling.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b1a7180868dd8d6a"}},{"code_sha256_prefix":"a4e183f24a5ad1a7","entry":"load_vocab","repo":"cbluebenchmark/cblue","repo_kind":"official","path":"cblue/models/zen/tokenization.py","file_url":"https://github.com/cbluebenchmark/cblue/blob/HEAD/cblue/models/zen/tokenization.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a4e183f24a5ad1a7"}},{"code_sha256_prefix":"3c241ecfe3749a6d","entry":"simple_accuracy","repo":"cbluebenchmark/cblue","repo_kind":"official","path":"cblue/metrics/cblue_metrics.py","file_url":"https://github.com/cbluebenchmark/cblue/blob/HEAD/cblue/metrics/cblue_metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3c241ecfe3749a6d"}},{"code_sha256_prefix":"7df01456f83e3edb","entry":"str_q2b","repo":"cbluebenchmark/cblue","repo_kind":"official","path":"cblue/utils.py","file_url":"https://github.com/cbluebenchmark/cblue/blob/HEAD/cblue/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7df01456f83e3edb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}