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

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2106.08087")

Code

Syntology Ran 4 of 16 code samples harvested from 1 repository linked to this paper; 12 have no recorded run. Of those that ran: 1 ran · honoured contract; 3 ran · our draft was wrong.

By repository: official repository: 16 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

cbluebenchmark/cblue officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
freedomintelligence/sdak mentioned on GitHubpytorchApache-2.0 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.

Code Syntology ran Syntology

16 samples harvested; 4 ran; 1 honoured the contract we drafted; 12 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
3ran · our draft was wrong
12unverified

Licence: 0 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. 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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

whitespace_tokenize cbluebenchmark/cblue/cblue/models/zen/tokenization.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · cf9ffa02a42184af · report
gelu cbluebenchmark/cblue/cblue/models/zen/modeling.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · fdc64f4c72036ae4 · report
prune_linear_layer cbluebenchmark/cblue/cblue/models/zen/modeling.py official repository ran · our draft was wrong Apache-2.0 (permissive) · d30d6c3098df2c42 · report
url_to_filename cbluebenchmark/cblue/cblue/models/zen/file_utils.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 5eff22fa0a651276 · report
cached_path cbluebenchmark/cblue/cblue/models/zen/file_utils.py official repository unverified Apache-2.0 (permissive) · cf9c448c96f48428 · report
convert_examples_to_features cbluebenchmark/cblue/cblue/models/zen/data.py official repository unverified Apache-2.0 (permissive) · d77c1cad6b941ff2 · report
convert_examples_to_features_for_tokens cbluebenchmark/cblue/cblue/models/zen/data.py official repository unverified Apache-2.0 (permissive) · 081479ed6ae40f0d · report
ctc_metric cbluebenchmark/cblue/cblue/metrics/cblue_metrics.py official repository unverified Apache-2.0 (permissive) · 0dd59e7198cafb75 · report
ee_metric cbluebenchmark/cblue/cblue/metrics/cblue_metrics.py official repository unverified Apache-2.0 (permissive) · f7aa06f500546846 · report
filename_to_url cbluebenchmark/cblue/cblue/models/zen/file_utils.py official repository unverified Apache-2.0 (permissive) · a6aab787fcf8b10d · report
load_dict cbluebenchmark/cblue/cblue/utils.py official repository unverified Apache-2.0 (permissive) · b26659d849aa4a63 · report
load_json cbluebenchmark/cblue/cblue/utils.py official repository unverified Apache-2.0 (permissive) · e02b2a940d01312d · report
load_tf_weights_in_bert cbluebenchmark/cblue/cblue/models/zen/modeling.py official repository unverified Apache-2.0 (permissive) · b1a7180868dd8d6a · report
load_vocab cbluebenchmark/cblue/cblue/models/zen/tokenization.py official repository unverified Apache-2.0 (permissive) · a4e183f24a5ad1a7 · report
simple_accuracy cbluebenchmark/cblue/cblue/metrics/cblue_metrics.py official repository unverified Apache-2.0 (permissive) · 3c241ecfe3749a6d · report
str_q2b cbluebenchmark/cblue/cblue/utils.py official repository unverified Apache-2.0 (permissive) · 7df01456f83e3edb · 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