Papers › Big Bird: Transformers for Longer Sequences

Big Bird: Transformers for Longer Sequences

28 Jul 2020NeurIPS 2020 12arXiv:2007.14062archive 2025-07-28

Manzil Zaheer, Guru Guruganesh, Avinava Dubey, Joshua Ainslie, Chris Alberti, Santiago Ontanon, Philip Pham, Anirudh Ravula, Qifan Wang, Li Yang, Amr Ahmed

Transformers-based models, such as BERT, have been one of the most successful deep learning models for NLP. Unfortunately, one of their core limitations is the quadratic dependency (mainly in terms of memory) on the sequence length due to their full attention mechanism. To remedy this, we propose, BigBird, a sparse attention mechanism that reduces this quadratic dependency to linear. We show that BigBird is a universal approximator of sequence functions and is Turing complete, thereby preserving these properties of the quadratic, full attention model. Along the way, our theoretical analysis reveals some of the benefits of having O(1) global tokens (such as CLS), that attend to the entire sequence as part of the sparse attention mechanism. The proposed sparse attention can handle sequences of length up to 8x of what was previously possible using similar hardware. As a consequence of the capability to handle longer context, BigBird drastically improves performance on various NLP tasks such as question answering and summarization. We also propose novel applications to genomics data.

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 15 code samples harvested from 3 repositories linked to this paper: 10 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 13 samples from 2 repositories, 9 ran (2 with no instrument failure; 7 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.

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

google-research/bigbird officialtfSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
facebookresearch/xformers mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Longformer: The Long-Document Transformer (arXiv:2004.05150; that paper's own run record: 22 ran (of which 4 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 8 where Syntology's instrument failed) · 13 unverified) and Self-attention Does Not Need O(n²) Memory (arXiv:2112.05682; that paper's own run record: 33 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 3 honoured, 6 violated, 12 with no contract checked; 12 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. 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
mim-solutions/bert_for_longer_texts mentioned on GitHubpytorchSyntology: 11 samples, 8 ran (6 instrument-failed) · 3 unverified report
mim-solutions/roberta_for_longer_texts mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
monologg/kobigbird mentioned on GitHubtfSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
sajjjadayobi/ParsBigBird mentioned on GitHubAGPL-3.0Syntology: not harvested report
sergeykramp/mthesis-bigbird-embeddings mentioned on GitHubpytorchSyntology: not harvested report
thefonseca/factorsum mentioned on GitHubpytorchSyntology: not harvested report
2024-MindSpore-1/Code2 mindsporeSyntology: not harvested 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
pwc-1/Paper-8 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models... (arXiv:2406.18321; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
pwc-1/Paper-8 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models... (arXiv:2406.18321; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
tensorflow/models tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); 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

15 samples harvested: 10 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 8 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
5ran · our draft was wrong
3ran; the contract check could not run
1ran
5unverified

Licence: 11 of the 15 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 3 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.

google-research/bigbird official repository 2 samples, 1 ran (1 instrument-failed) · 1 unverified
create_rand_mask_from_inputs bigbird/core/attention.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) · 44d0dd1eff48b3db · report fixture: signature from_blocked_mask:EagerTensor/3/float, to_blocked_mask:EagerTensor/3/float, rand_attn:EagerTensor/4/int, num_attention_heads:int/0/int, num_rand_blocks:int/0/int, from_seq_length:int/0/int, from_block_size:int/0/int · returned EagerTensor · level recorded 2026-09-22
bigbird_block_sparse_attention bigbird/core/attention.py unverified Apache-2.0 (permissive) · 0d09b5689924a10b · report
mim-solutions/bert_for_longer_texts community (archive-listed) 11 samples, 8 ran (6 instrument-failed) · 3 unverified
InconsistentSplittingParamsException belt_nlp/splitting.py ran · metamorphic tier: deterministic licence not identified · pointer only · e4b0ec678a1f3059 · report fixture: returned InconsistentSplittingParamsException · level recorded 2026-09-22
split_overlapping belt_nlp/splitting.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic licence not identified · pointer only · c91a4a5114716579 · report fixture: signature tensor:Tensor/1/float, chunk_size:int/0/int, stride:int/0/int, minimal_chunk_length:int/0/int · returned list · level recorded 2026-09-22
split_tokens_into_smaller_chunks belt_nlp/splitting.py ran · our draft was wrong licence not identified · pointer only · 0ce3135e26fafb14 · report fixture: signature tokens:BatchEncoding/0/?, chunk_size:int/0/int, stride:int/0/int, minimal_chunk_length:int/0/int · returned tuple · level recorded 2026-09-22
stack_tokens_from_all_chunks belt_nlp/splitting.py ran · our draft was wrong licence not identified · pointer only · 15b2fccc82d0a62a · report fixture: signature input_id_chunks:list/1/Tensor, mask_chunks:list/1/Tensor · returned tuple · level recorded 2026-09-22
tokenize_text_with_truncation belt_nlp/splitting.py ran · our draft was wrong licence not identified · pointer only · 4123d6b63df245f2 · report fixture: signature text:str/0/str, tokenizer:callable/0/?, maximal_text_length:int/0/int · returned BatchEncoding · level recorded 2026-09-22
tokenize_whole_text belt_nlp/splitting.py ran · our draft was wrong licence not identified · pointer only · 316d08e3b6936972 · report fixture: signature text:str/0/str, tokenizer:callable/0/? · returned BatchEncoding · level recorded 2026-09-22
transform_list_of_texts belt_nlp/splitting.py ran · our draft was wrong licence not identified · pointer only · 41d96f44b38351ac · report fixture: signature texts:list/1/str, tokenizer:callable/0/?, chunk_size:int/0/int, stride:int/0/int, minimal_chunk_length:int/0/int, maximal_text_length:int/0/int · returned BatchEncoding · level recorded 2026-09-22
transform_single_text belt_nlp/splitting.py ran · honoured contract licence not identified · pointer only · 4d240665f4cb4490 · report fixture: signature text:str/0/str, tokenizer:callable/0/?, chunk_size:int/0/int, stride:int/0/int, minimal_chunk_length:int/0/int, maximal_text_length:NoneType/0/? · returned tuple · level recorded 2026-09-22
add_padding_tokens belt_nlp/splitting.py unverified licence not identified · pointer only · 4603a2fe10eb193d · report
add_special_tokens_at_beginning_and_end belt_nlp/splitting.py unverified licence not identified · pointer only · dd7b545b8b9f7fed · report
check_split_parameters_consistency belt_nlp/splitting.py unverified licence not identified · pointer only · e219be299ea45b2d · report
monologg/kobigbird community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
create_rand_mask_from_inputs pretrain/kobigbird/attention.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) · 2c5945c3b5a80279 · report fixture: signature from_blocked_mask:EagerTensor/3/float, to_blocked_mask:EagerTensor/3/float, rand_attn:EagerTensor/4/int, num_attention_heads:int/0/int, num_rand_blocks:int/0/int, from_seq_length:int/0/int, from_block_size:int/0/int · returned EagerTensor · level recorded 2026-09-22
bigbird_block_sparse_attention pretrain/kobigbird/attention.py unverified Apache-2.0 (permissive) · b18d818e15d8f5f2 · 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.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

harvested Assembly for BIGBIRD (graph method: BIGBIRD). 2 bricks; individually on a fixture: 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) · 1 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. bigbird_block_sparse_attention entry · level 0 · unverified · 0d09b5689924a10b
  2. create_rand_mask_from_inputs helper · level 1 · ran; the contract check could not run (RAISES) · 44d0dd1eff48b3db

harvested Assembly for BIGBIRD (graph method: BIGBIRD). 11 bricks; individually on a fixture: 8 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. transform_list_of_texts entry · level 1 · ran · our draft was wrong · 41d96f44b38351ac
  2. transform_single_text helper · level 1 · ran · honoured contract · 4d240665f4cb4490
  3. add_padding_tokens data_transform · level 0 · unverified · 4603a2fe10eb193d
  4. add_special_tokens_at_beginning_and_end data_transform · level 0 · unverified · dd7b545b8b9f7fed
  5. split_tokens_into_smaller_chunks data_transform · level 1 · ran · our draft was wrong · 0ce3135e26fafb14
  6. stack_tokens_from_all_chunks data_transform · level 1 · ran · our draft was wrong · 15b2fccc82d0a62a
  7. tokenize_text_with_truncation data_transform · level 1 · ran · our draft was wrong · 4123d6b63df245f2
  8. tokenize_whole_text data_transform · level 1 · ran · our draft was wrong · 316d08e3b6936972
  9. split_overlapping helper · level 1 · ran; the contract check could not run (RAISES) · c91a4a5114716579
  10. check_split_parameters_consistency helper · level 0 · unverified · e219be299ea45b2d
  11. InconsistentSplittingParamsException helper · level 1 · ran · e4b0ec678a1f3059

harvested Assembly for BIGBIRD (graph method: BIGBIRD). 2 bricks; individually on a fixture: 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) · 1 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. bigbird_block_sparse_attention entry · level 0 · unverified · b18d818e15d8f5f2
  2. create_rand_mask_from_inputs helper · level 1 · ran; the contract check could not run (RAISES) · 2c5945c3b5a80279

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="2007.14062") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Linguistic AcceptabilityNatural Language InferenceQuestion AnsweringSemantic Textual SimilarityText ClassificationText Summarization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Document Summarization BBC XSum BigBird-Pegasus ROUGE-1 47.12 #1 of 1 Archive leaderboard report
Document Summarization BBC XSum BigBird-Pegasus ROUGE-2 24.05 #1 of 1 Archive leaderboard report
Document Summarization BBC XSum BigBird-Pegasus ROUGE-L 38.8 #1 of 1 Archive leaderboard report
Document Summarization CNN / Daily Mail BigBird-Pegasus ROUGE-1 43.84 #10 of 26 Archive leaderboard report
Document Summarization CNN / Daily Mail BigBird-Pegasus ROUGE-2 21.11 #10 of 26 Archive leaderboard report
Document Summarization CNN / Daily Mail BigBird-Pegasus ROUGE-L 40.74 #10 of 26 Archive leaderboard report
Linguistic Acceptability CoLA BigBird Accuracy 58.5% #32 of 43 Archive leaderboard report
Natural Language Inference MultiNLI BigBird Matched 87.5 #22 of 67 Archive leaderboard report
Natural Language Inference QNLI BigBird Accuracy 92.2% #26 of 43 Archive leaderboard report
Natural Language Inference RTE BigBird Accuracy 75.0% #44 of 90 Archive leaderboard report
Question Answering HotpotQA BigBird-etc ANS-F1 0.755 #2 of 72 Archive leaderboard report
Question Answering HotpotQA BigBird-etc JOINT-F1 0.736 #2 of 72 Archive leaderboard report
Question Answering HotpotQA BigBird-etc SUP-F1 0.891 #2 of 72 Archive leaderboard report
Question Answering Quora Question Pairs BigBird Accuracy 88.6% #15 of 19 Archive leaderboard report
Question Answering TriviaQA BigBird-etc F1 80.9 #49 of 56 Archive leaderboard report
Question Answering WikiHop BigBird-etc Test 82.3 #1 of 9 Archive leaderboard report
Semantic Textual Similarity MRPC BigBird F1 91.5 #38 of 45 Archive leaderboard report
Semantic Textual Similarity STS Benchmark BigBird Spearman Correlation .878 #39 of 66 Archive leaderboard report
Sentiment Analysis SST-2 Binary classification BigBird Accuracy 94.6 #34 of 87 Archive leaderboard report
Text Classification Arxiv HEP-TH citation graph BigBird Accuracy 92.31 #1 of 1 Archive leaderboard report
Text Classification Hyperpartisan BigBird Accuracy 92.2 #1 of 1 Archive leaderboard report
Text Classification Patents BigBird Accuracy 69.3 #1 of 1 Archive leaderboard report
Text Classification Yelp-5 BigBird Accuracy 72.16% #3 of 7 Archive leaderboard report
Text Summarization BigPatent BigBird-Pegasus ROUGE-1 60.64 #2 of 2 Archive leaderboard report
Text Summarization BigPatent BigBird-Pegasus ROUGE-2 42.46 #2 of 2 Archive leaderboard report
Text Summarization BigPatent BigBird-Pegasus ROUGE-L 50.01 #2 of 2 Archive leaderboard report
Text Summarization Pubmed BigBird-Pegasus ROUGE-1 46.32 #15 of 29 Archive leaderboard report
Text Summarization Pubmed BigBird-Pegasus ROUGE-2 20.65 #15 of 29 Archive leaderboard report
Text Summarization Pubmed BigBird-Pegasus ROUGE-L 42.33 #15 of 29 Archive leaderboard report
Text Summarization arXiv BigBird-Pegasus ROUGE-1 46.63 #1 of 1 Archive leaderboard report
Text Summarization arXiv BigBird-Pegasus ROUGE-2 19.02 #1 of 1 Archive leaderboard report
Text Summarization arXiv BigBird-Pegasus ROUGE-L 41.77 #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

Introduced by this paper: BigBird

BigBird

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