Papers › GLM: General Language Model Pretraining with Autoregressive Blank Infilling

GLM: General Language Model Pretraining with Autoregressive Blank Infilling

18 Mar 2021ACL 2022 5arXiv:2103.10360archive 2025-07-28

Zhengxiao Du, Yujie Qian, Xiao Liu, Ming Ding, Jiezhong Qiu, Zhilin Yang, Jie Tang

There have been various types of pretraining architectures including autoencoding models (e.g., BERT), autoregressive models (e.g., GPT), and encoder-decoder models (e.g., T5). However, none of the pretraining frameworks performs the best for all tasks of three main categories including natural language understanding (NLU), unconditional generation, and conditional generation. We propose a General Language Model (GLM) based on autoregressive blank infilling to address this challenge. GLM improves blank filling pretraining by adding 2D positional encodings and allowing an arbitrary order to predict spans, which results in performance gains over BERT and T5 on NLU tasks. Meanwhile, GLM can be pretrained for different types of tasks by varying the number and lengths of blanks. On a wide range of tasks across NLU, conditional and unconditional generation, GLM outperforms BERT, T5, and GPT given the same model sizes and data, and achieves the best performance from a single pretrained model with 1.25x parameters of BERT Large , demonstrating its generalizability to different downstream tasks.

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

No sample from the archive's official repository (THUDM/GLM) is linked to this paper; the 1 sample below comes from 1 community repository. Syntology harvested code from THUDM/GLM for another paper.

THUDM/GLM: Syntology's graph links these samples to GLM-130B: An Open Bilingual Pre-trained Model (arXiv:2210.02414; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method.

Syntology 1 code sample harvested from 1 repository linked to this paper: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: community (archive-listed): 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 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 5 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

THUDM/GLM officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to GLM-130B: An Open Bilingual Pre-trained Model (arXiv:2210.02414; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
BBuf/GLM mentioned on GitHubpytorchSyntology: not harvested report
thudm/chatglm mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools (arXiv:2406.12793; that paper's own run record: 21 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
thudm/chatglm2-6b mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
thudm/chatglm3 mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to GLM-130B: An Open Bilingual Pre-trained Model (arXiv:2210.02414; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
thudm/swissarmytransformer mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
thudm/visualglm-6b mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to TheoremQA: A Theorem-driven Question Answering dataset (arXiv:2305.12524; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
jackaduma/ChatGLM-LoRA-RLHF-PyTorch pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to GLM-130B: An Open Bilingual Pre-trained Model (arXiv:2210.02414; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 6 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

1 sample harvested: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure 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 · our draft was wrong

Licence: 0 of the 1 sample 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 thudm/swissarmytransformer. “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.

thudm/swissarmytransformer community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_masks_and_position_ids_glm examples/glm/inference_glm.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 562eb223eab20399 · report fixture: signature seq:Tensor/1/int, mask_position:int/0/int, context_length:int/0/int · returned tuple · level recorded 2026-09-22

Tasks

Abstractive Text SummarizationClassificationDecoderDocument SummarizationGeneral ClassificationLanguage ModelingLanguage ModellingNatural Language Understanding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Abstractive Text Summarization CNN / Daily Mail GLM-XXLarge ROUGE-1 44.7 #9 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail GLM-XXLarge ROUGE-2 21.4 #9 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail GLM-XXLarge ROUGE-L 41.4 #9 of 53 Archive leaderboard report
Document Summarization CNN / Daily Mail GLM-XXLarge ROUGE-1 44.7 #4 of 26 Archive leaderboard report
Document Summarization CNN / Daily Mail GLM-XXLarge ROUGE-2 21.4 #4 of 26 Archive leaderboard report
Document Summarization CNN / Daily Mail GLM-XXLarge ROUGE-L 41.4 #4 of 26 Archive leaderboard report
Language Modelling LAMBADA GLM-XXLarge (bidirectional) Accuracy 72.35 #21 of 37 Archive leaderboard report
Language Modelling LAMBADA GLM-XXLarge (unidirectional) Accuracy 67.18 #27 of 37 Archive leaderboard report
Language Modelling WikiText-103 GLM-XXLarge (bidirectional) Number of params 10000M #4 of 89 Archive leaderboard report
Language Modelling WikiText-103 GLM-XXLarge (bidirectional) Test perplexity 11.33 #4 of 89 Archive leaderboard report
Language Modelling WikiText-103 GLM-XXLarge (unidirectional) Number of params 10000M #5 of 89 Archive leaderboard report
Language Modelling WikiText-103 GLM-XXLarge (unidirectional) Test perplexity 12.22 #5 of 89 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

AdafactorAdamAttentionAttention DropoutBERTBPECosine AnnealingDense ConnectionsDiscriminative Fine-TuningDropoutGPTGated Linear UnitInverse Square Root ScheduleLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSentencePieceSoftmaxT5Weight DecayWordPiece

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