Papers › XLNet: Generalized Autoregressive Pretraining for Language Understanding

XLNet: Generalized Autoregressive Pretraining for Language Understanding

19 Jun 2019NeurIPS 2019 12arXiv:1906.08237archive 2025-07-28

Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Ruslan Salakhutdinov, Quoc V. Le

With the capability of modeling bidirectional contexts, denoising autoencoding based pretraining like BERT achieves better performance than pretraining approaches based on autoregressive language modeling. However, relying on corrupting the input with masks, BERT neglects dependency between the masked positions and suffers from a pretrain-finetune discrepancy. In light of these pros and cons, we propose XLNet, a generalized autoregressive pretraining method that (1) enables learning bidirectional contexts by maximizing the expected likelihood over all permutations of the factorization order and (2) overcomes the limitations of BERT thanks to its autoregressive formulation. Furthermore, XLNet integrates ideas from Transformer-XL, the state-of-the-art autoregressive model, into pretraining. Empirically, under comparable experiment settings, XLNet outperforms BERT on 20 tasks, often by a large margin, including question answering, natural language inference, sentiment analysis, and document ranking.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 24 code samples harvested from 6 repositories linked to this paper: 15 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 22 samples from 5 repositories, 14 ran (9 with no instrument failure; 5 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 10 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. 2 of the 15 samples that ran have no recorded date.

27 repositories listed; official and paper-mentioned ones first.

zihangdai/xlnet officialmentioned in papermentioned on GitHubtfSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
2miatran/Natural-Language-Processing mentioned on GitHubSyntology: not harvested report
NathanDuran/Sentence-Encoding-for-DA-Classification mentioned on GitHubtfGPL-3.0Syntology: not harvested report
SambhawDrag/XLNet.jl mentioned on GitHubpytorchSyntology: not harvested report
chesterdu/contrastive_summary mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
cuhksz-nlp/SAPar mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improving Constituency Parsing with Span Attention (arXiv:2010.07543; that paper's own run record: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result); nothing checks that they implement this paper's method. report
facebookresearch/anli mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
fanchenyou/transformer-study mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
graykode/xlnet-Pytorch mentioned on GitHubpytorchSyntology: not harvested report
https-seyhan/BugAI mentioned on GitHubSyntology: not harvested report
huggingface/transformers mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified), HuggingFace's Transformers: State-of-the-art Natural Language Processing (arXiv:1910.03771; that paper's own run record: 3 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; 3 where Syntology's instrument failed) · 0 unverified), DeBERTa: Decoding-enhanced BERT with Disentangled Attention (arXiv:2006.03654; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
huggingface/xlnet mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context (arXiv:1901.02860; that paper's own run record: 67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified); nothing checks that they implement this paper's method. report
jonahwinninghoff/Text-Summarization mentioned on GitHubtfSyntology: not harvested report
joshuaWang-bit/Textclassification-pytorch mentioned on GitHubpytorchSyntology: not harvested report
kaushaltrivedi/fast-bert mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (arXiv:1810.04805; that paper's own run record: 300 ran (of which 75 constructed an object rather than computing a result; 234 with no instrument failure: 18 honoured, 5 violated, 211 with no contract checked; 66 where Syntology's instrument failed) · 359 unverified) and RoBERTa: A Robustly Optimized BERT Pretraining Approach (arXiv:1907.11692; that paper's own run record: 37 ran (of which 11 constructed an object rather than computing a result; 36 with no instrument failure: 2 honoured, 0 violated, 34 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
listenviolet/XLNet mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context (arXiv:1901.02860; that paper's own run record: 67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified); nothing checks that they implement this paper's method. report
pauldevos/python-notes mentioned on GitHubpytorchSyntology: not harvested report
samwisegamjeee/pytorch-transformers mentioned on GitHubpytorchApache-2.0Syntology: 17 samples, 11 ran (5 instrument-failed) · 6 unverified report
tomgoter/nlp_finalproject mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unsupervised Data Augmentation for Consistency Training (arXiv:1904.12848; that paper's own run record: 30 ran (of which 3 constructed an object rather than computing a result; 22 with no instrument failure: 2 honoured, 0 violated, 20 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified); nothing checks that they implement this paper's method. report
utterworks/fast-bert mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
zaradana/Fast_BERT mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
MS-P3/code7 mindsporeSyntology: not harvested report
MindCode-4/code-5 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ViTamin: Designing Scalable Vision Models in the Vision-Language Era (arXiv:2404.02132; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
PaddlePaddle/PaddleNLP paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ERNIE 3.0 Tiny: Frustratingly Simple Method to Improve Task-Agnostic Distillation... (arXiv:2301.03416; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
lvyufeng/bert4ms mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RoBERTa: A Robustly Optimized BERT Pretraining Approach (arXiv:1907.11692; that paper's own run record: 37 ran (of which 11 constructed an object rather than computing a result; 36 with no instrument failure: 2 honoured, 0 violated, 34 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
pwc-1/Paper-9 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RandAugment: Practical automated data augmentation with a reduced search space (arXiv:1909.13719; that paper's own run record: 58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
pwc-1/Paper-9 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RandAugment: Practical automated data augmentation with a reduced search space (arXiv:1909.13719; that paper's own run record: 58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 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

24 samples harvested: 15 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 9 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.

2ran · honoured contract
5ran · our draft was wrong
8ran
9unverified

Licence: 4 of the 24 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 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 6 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

zihangdai/xlnet official repository 2 samples, 1 ran (0 instrument-failed) · 1 unverified
relative_positional_encoding modeling.py ran · honoured contract Apache-2.0 (permissive) · 4276ef7411886c72 · report fixture: signature qlen:int/0/int, klen:int/0/int, d_model:int/0/int, clamp_len:int/0/int, attn_type:str/0/str, bi_data:bool/0/bool, bsz:int/0/int, dtype:DType/0/? · returned EagerTensor · level recorded 2026-09-22
transformer_xl modeling.py unverified Apache-2.0 (permissive) · 346015e252bc02c1 · report
chesterdu/contrastive_summary community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
SupConLoss in 21 papers src/model.py ran no licence file found · pointer only · 624bba127433de69 · report fixture: signature features:Tensor/3/float, labels:Tensor/1/int, mask:NoneType/0/? · returned Tensor · level recorded 2026-09-24
scl_model_Xlnet src/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 1370bb66bcbac8f1 · report fixture: returned scl_model_Xlnet · level recorded 2026-09-22
fanchenyou/transformer-study community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
XLNet transformer_xlnet_4.py ran no licence file found · pointer only · 30647553d552c86f · report fixture: returned XLNet · level recorded 2026-09-22
samwisegamjeee/pytorch-transformers community (archive-listed) 17 samples, 11 ran (5 instrument-failed) · 6 unverified
swish in 258 papers
census: 14 implementations from 37 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
pytorch_transformers/modeling_bert.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 0f786c407fb1ee4c · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
build_tf_to_pytorch_map in 14 papers pytorch_transformers/modeling_transfo_xl.py ran · our draft was wrong Apache-2.0 (permissive) · 35ef111fc00c21b4 · report fixture: signature model:callable/0/?, config:Config/0/? · returned dict · level recorded 2026-09-22
build_tf_xlnet_to_pytorch_map in 6 papers pytorch_transformers/modeling_xlnet.py ran Apache-2.0 (permissive) · c92ba449e48ecffe · report fixture: signature model:callable/0/?, config:Config/0/?, tf_weights:dict/0/? · returned dict · 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
pytorch_transformers/modeling_gpt2.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 8d23fbe2b99b840b · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
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
pytorch_transformers/modeling_bert.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
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input
pytorch_transformers/modeling_xlnet.py ran fingerprinted Apache-2.0 (permissive) · b05b2bb38c0e4e72 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-25
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input
pytorch_transformers/modeling_xlm.py ran fingerprinted Apache-2.0 (permissive) · b3c2618f6b7fb60c · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-25
get_masks in 23 papers pytorch_transformers/modeling_xlm.py ran Apache-2.0 (permissive) · f5d8d44f65a08b76 · report fixture: signature slen:int/0/int, lengths:Tensor/1/int, causal:bool/0/bool, padding_mask:NoneType/0/? · returned tuple · level recorded 2026-09-25
prune_conv1d_layer in 20 papers pytorch_transformers/modeling_utils.py ran Apache-2.0 (permissive) · 7183a17dd79327a8 · report fixture: signature layer:callable/0/?, index:Tensor/1/int, dim:int/0/int · returned Conv1D · level recorded 2026-09-25
prune_linear_layer in 40 papers pytorch_transformers/modeling_utils.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
sample_logits in 16 papers pytorch_transformers/modeling_transfo_xl_utilities.py ran · our draft was wrong Apache-2.0 (permissive) · 93228a3eb5c4d179 · report fixture: signature embedding:callable/0/?, bias:Tensor/1/float, labels:Tensor/2/int, inputs:Tensor/3/float, sampler:LogUniformSampler/0/? · returned Tensor · level recorded 2026-09-22
load_tf_weights_in_bert in 135 papers pytorch_transformers/modeling_bert.py unverified Apache-2.0 (permissive) · 03a94dbb436249a3 · report
load_tf_weights_in_gpt2 in 68 papers pytorch_transformers/modeling_gpt2.py unverified Apache-2.0 (permissive) · 07bb0220eb5b609f · report
load_tf_weights_in_openai_gpt in 13 papers pytorch_transformers/modeling_openai.py unverified Apache-2.0 (permissive) · 42ee168c3ae12e60 · report
load_tf_weights_in_transfo_xl in 12 papers pytorch_transformers/modeling_transfo_xl.py unverified Apache-2.0 (permissive) · 23d246e59ef9447b · report
load_tf_weights_in_xlnet in 6 papers pytorch_transformers/modeling_xlnet.py unverified Apache-2.0 (permissive) · 4a94662ff3b5c5cf · report
prune_layer in 8 papers pytorch_transformers/modeling_utils.py unverified Apache-2.0 (permissive) · e31093ffc8275cff · report
utterworks/fast-bert community (archive-listed) 1 sample, 0 ran · 1 unverified
XLNetForMultiLabelSequenceClassification fast_bert/modeling.py unverified Apache-2.0 (permissive) · de032896e6064f69 · report
zaradana/Fast_BERT community (archive-listed) 1 sample, 0 ran · 1 unverified
XLNetForMultiLabelSequenceClassification 0_fast_bert/modeling.py unverified Apache-2.0 (permissive) · ea4abb20faaddb4d · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

5 assemblies on this paper: 5 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

5 sibling assemblies for XLNet (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for XLNet (graph method: XLNet). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. scl_model_Xlnet entry · level 1 · ran · 1370bb66bcbac8f1
  2. SupConLoss helper · level 1 · ran · 624bba127433de69

harvested Assembly for XLNet (graph method: XLNet). 14 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. transformer_xl entry · level 0 · unverified · 346015e252bc02c1
  2. _cache_mem helper · level 1 · ran; the contract check could not run · 9d5e914b24b8911a
  3. _create_mask helper · level 0 · unverified · c1f8a649a7a837d5
  4. embedding_lookup helper · level 0 · unverified · 5abf0267f0fc7514
  5. positionwise_ffn model · level 0 · unverified · ddf11fc956cd28ce
  6. rel_multihead_attn model · level 0 · unverified · 6ccb8d28491109b6
  7. relative_positional_encoding model · level 1 · ran · honoured contract · 4276ef7411886c72
  8. two_stream_rel_attn model · level 0 · unverified · 2d935f29546db9cd
  9. gelu helper · level 1 · ran · honoured contract · d08f324f950148de
  10. head_projection model · level 0 · unverified · 6804d62cb7cd8df3
  11. post_attention model · level 0 · unverified · cf208c8c20d52c1b
  12. rel_attn_core model · level 0 · unverified · b517847a8c809203
  13. positional_embedding helper · level 1 · ran; the contract check could not run · 9bf0f6e6298f3fbe
  14. rel_shift model · level 1 · ran; the contract check could not run · 5f7c5b38aeb29bf5

harvested Assembly for XLNet (graph method: XLNet). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 5 siblings

  1. XLNet entry · level 1 · ran · 30647553d552c86f

harvested Assembly for XLNet (graph method: XLNet). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. XLNetForMultiLabelSequenceClassification entry · level 0 · unverified · ea4abb20faaddb4d

harvested Assembly for XLNet (graph method: XLNet). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. XLNetForMultiLabelSequenceClassification entry · level 0 · unverified · de032896e6064f69

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1906.08237") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Audio Question AnsweringChinese Reading ComprehensionDocument RankingHumor DetectionLanguage ModelingLanguage ModellingNatural Language InferenceParaphrase IdentificationQuestion AnsweringReading ComprehensionSemantic Textual SimilaritySentiment AnalysisText Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Document Ranking ClueWeb09-B XLNet ERR@20 20.28 #1 of 1 Archive leaderboard report
Document Ranking ClueWeb09-B XLNet nDCG@20 31.10 #1 of 1 Archive leaderboard report
Humor Detection 200k Short Texts for Humor Detection XLNet Large Cased F1-score 0.920 #2 of 6 Archive leaderboard report
Linguistic Acceptability CoLA XLNet (single model) Accuracy 69% #15 of 43 Archive leaderboard report
Natural Language Inference ANLI test XLNet (Large) A1 70.3 #7 of 25 Archive leaderboard report
Natural Language Inference ANLI test XLNet (Large) A2 50.9 #7 of 25 Archive leaderboard report
Natural Language Inference ANLI test XLNet (Large) A3 49.4 #7 of 25 Archive leaderboard report
Natural Language Inference MultiNLI XLNet (single model) Matched 90.8 #10 of 67 Archive leaderboard report
Natural Language Inference QNLI XLNet (single model) Accuracy 94.9% #11 of 43 Archive leaderboard report
Natural Language Inference RTE XLNet (single model) Accuracy 85.9% #24 of 90 Archive leaderboard report
Natural Language Inference WNLI XLNet Accuracy 92.5 #4 of 23 Archive leaderboard report
Paraphrase Identification Quora Question Pairs XLNet-Large (ensemble) Accuracy 90.3 #7 of 31 Archive leaderboard report
Paraphrase Identification Quora Question Pairs XLNet-Large (ensemble) F1 74.2 #7 of 31 Archive leaderboard report
Question Answering Quora Question Pairs XLNet (single model) Accuracy 92.3% #1 of 19 Archive leaderboard report
Question Answering RACE XLNet RACE 81.75 #1 of 7 Archive leaderboard report
Question Answering RACE XLNet RACE-m 85.45 #1 of 7 Archive leaderboard report
Question Answering SQuAD1.1 XLNet (single model) EM 89.898 #6 of 213 Archive leaderboard report
Question Answering SQuAD1.1 XLNet (single model) F1 95.080 #6 of 213 Archive leaderboard report
Question Answering SQuAD1.1 XLNet (single model) Hardware Burden 46449G #6 of 213 Archive leaderboard report
Question Answering SQuAD1.1 dev XLNet (single model) EM 89.7 #4 of 55 Archive leaderboard report
Question Answering SQuAD1.1 dev XLNet (single model) F1 95.1 #4 of 55 Archive leaderboard report
Question Answering SQuAD2.0 XLNet (single model) EM 87.926 #77 of 286 Archive leaderboard report
Question Answering SQuAD2.0 XLNet (single model) F1 90.689 #77 of 286 Archive leaderboard report
Question Answering SQuAD2.0 dev XLNet (single model) EM 87.9 #1 of 13 Archive leaderboard report
Question Answering SQuAD2.0 dev XLNet (single model) F1 90.6 #1 of 13 Archive leaderboard report
Reading Comprehension RACE XLNet Accuracy (High) 84.0 #11 of 24 Archive leaderboard report
Reading Comprehension RACE XLNet Accuracy (Middle) 88.6 #11 of 24 Archive leaderboard report
Semantic Textual Similarity MRPC XLNet (single model) Accuracy 90.8% #9 of 45 Archive leaderboard report
Semantic Textual Similarity STS Benchmark XLNet (single model) Pearson Correlation 0.925 #6 of 66 Archive leaderboard report
Semantic Textual Similarity SentEval XLNet-Large MRPC 93.0/90.7 #6 of 6 Archive leaderboard report
Semantic Textual Similarity SentEval XLNet-Large SICK-E - #6 of 6 Archive leaderboard report
Semantic Textual Similarity SentEval XLNet-Large SICK-R - #6 of 6 Archive leaderboard report
Semantic Textual Similarity SentEval XLNet-Large STS 91.6/91.1* #6 of 6 Archive leaderboard report
Sentiment Analysis IMDb XLNet Accuracy 96.21 #3 of 49 Archive leaderboard report
Sentiment Analysis SST-2 Binary classification XLNet (single model) Accuracy 97 #7 of 87 Archive leaderboard report
Sentiment Analysis SST-2 Binary classification XLNet-Large (ensemble) Accuracy 96.8 #10 of 87 Archive leaderboard report
Sentiment Analysis Yelp Binary classification XLNet Error 1.37 #1 of 20 Archive leaderboard report
Sentiment Analysis Yelp Fine-grained classification XLNet Error 27.05 #1 of 17 Archive leaderboard report
Text Classification AG News XLNet Error 4.45 #1 of 24 Archive leaderboard report
Text Classification Amazon-2 XLNet Error 2.11 #1 of 4 Archive leaderboard report
Text Classification Amazon-5 XLNet Error 31.67 #1 of 3 Archive leaderboard report
Text Classification DBpedia XLNet Error 0.62 #1 of 21 Archive leaderboard report
Text Classification Yelp-2 XLNet Accuracy 98.63% #1 of 5 Archive leaderboard report
Text Classification Yelp-5 XLNet Accuracy 72.95% #2 of 7 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

AdamAdaptive Input RepresentationsAdaptive SoftmaxAttentionBPECosine AnnealingDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingLinear Warmup With Linear DecayMulti-Head AttentionReLUResidual ConnectionSentencePieceSoftmaxTransformer-XLVariational DropoutXLNet

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