Papers › CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark

CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark

15 Jun 2021ACL 2022 5arXiv:2106.08087archive 2025-07-28

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

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 https://tianchi.aliyun.com/dataset/dataDetail?dataId=95414&lang=en-us.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 11 ran (8 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 11 samples that ran has no recorded date.

cbluebenchmark/cblue officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 16 samples, 11 ran (3 instrument-failed) · 5 unverified report
freedomintelligence/sdak mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for... (arXiv:2307.13528; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

16 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
3ran · our draft was wrong
7ran
5unverified

Licence: 2 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from cbluebenchmark/cblue. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

cbluebenchmark/cblue official repository 16 samples, 11 ran (3 instrument-failed) · 5 unverified
whitespace_tokenize in 49 papers cblue/models/zen/tokenization.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · cf9ffa02a42184af · report fixture: signature text:str/0/str · returned list · level recorded, date not recorded
convert_examples_to_features in 134 papers cblue/models/zen/data.py ran Apache-2.0 (permissive) · d77c1cad6b941ff2 · report fixture: signature text1:list/1/str, max_seq_length:int/0/int, tokenizer:MinimalTokenizer/0/?, ngram_dict:MinimalNgramDict/0/?, text2:list/1/str, return_tensors:bool/0/bool · returned dict · level recorded 2026-09-25
ctc_metric cblue/metrics/cblue_metrics.py ran fingerprinted Apache-2.0 (permissive) · 0dd59e7198cafb75 · report fixture: signature preds:ndarray/1/int, labels:ndarray/1/int · returned tuple · level recorded 2026-09-25
ee_metric cblue/metrics/cblue_metrics.py ran fingerprinted Apache-2.0 (permissive) · f7aa06f500546846 · report fixture: signature preds:ndarray/1/int, labels:ndarray/1/int · returned tuple · level recorded 2026-09-25
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
cblue/models/zen/modeling.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · fdc64f4c72036ae4 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
load_dict in 29 papers cblue/utils.py ran Apache-2.0 (permissive) · b26659d849aa4a63 · report fixture: signature dict_path:str/0/str · returned dict · level recorded 2026-09-25
load_json in 344 papers cblue/utils.py ran Apache-2.0 (permissive) · e02b2a940d01312d · report fixture: signature input_file:str/0/str · returned list · level recorded 2026-09-25
load_vocab in 107 papers cblue/models/zen/tokenization.py ran Apache-2.0 (permissive) · a4e183f24a5ad1a7 · report fixture: signature vocab_file:str/0/str · returned OrderedDict · level recorded 2026-09-25
prune_linear_layer in 40 papers cblue/models/zen/modeling.py ran · our draft was wrong Apache-2.0 (permissive) · d30d6c3098df2c42 · report fixture: signature layer:callable/0/?, index:Tensor/1/int, dim:int/0/int · returned Linear · level recorded 2026-09-22
str_q2b cblue/utils.py ran fingerprinted Apache-2.0 (permissive) · 7df01456f83e3edb · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-25
url_to_filename in 73 papers cblue/models/zen/file_utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 5eff22fa0a651276 · report fixture: signature url:str/0/str, etag:str/0/str · returned str · level recorded 2026-09-22
cached_path in 47 papers cblue/models/zen/file_utils.py unverified Apache-2.0 (permissive) · cf9c448c96f48428 · report
convert_examples_to_features_for_tokens cblue/models/zen/data.py unverified Apache-2.0 (permissive) · 081479ed6ae40f0d · report
filename_to_url in 54 papers cblue/models/zen/file_utils.py unverified Apache-2.0 (permissive) · a6aab787fcf8b10d · report
load_tf_weights_in_bert in 135 papers cblue/models/zen/modeling.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · b1a7180868dd8d6a · report
simple_accuracy in 66 papers cblue/metrics/cblue_metrics.py unverified Apache-2.0 (permissive) · 3c241ecfe3749a6d · report

Tasks

Intent ClassificationMedical Concept NormalizationMedical Relation ExtractionNamed Entity RecognitionNamed Entity Recognition (NER)Natural Language InferenceSemantic SimilaritySentenceSentence ClassificationSentence-Pair Classification

Datasets

Introduced by this paper, per the archive.

CHIP-CDNCHIP-STSCMeEEKUAKE-QICKUAKE-QQRKUAKE-QTR

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Intent Classification KUAKE-QIC RoBERTa-wwm-ext-base Accuracy 85.5 #1 of 1 Archive leaderboard report
Medical Relation Extraction CMeIE RoBERTa-wwm-ext-large Micro F1 55.9 #1 of 1 Archive leaderboard report
Named Entity Recognition (NER) CMeEE MacBERT-large Micro F1 62.4 #2 of 2 Archive leaderboard report
Natural Language Inference KUAKE-QQR BERT-base Accuracy 84.7 #1 of 1 Archive leaderboard report
Natural Language Inference KUAKE-QTR MacBERT-large Accuracy 62.9 #1 of 1 Archive leaderboard report
Semantic Similarity CHIP-STS MacBERT-large Macro F1 85.6 #1 of 1 Archive leaderboard report
Sentence Classification CHIP-CTC RoBERTa-large Macro F1 70.9 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ALBERTBERTRoBERTa

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections