Papers › Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

23 Oct 2019arXiv 2019 10arXiv:1910.10683archive 2025-07-28

Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu

Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts all text-based language problems into a text-to-text format. Our systematic study compares pre-training objectives, architectures, unlabeled data sets, transfer approaches, and other factors on dozens of language understanding tasks. By combining the insights from our exploration with scale and our new ``Colossal Clean Crawled Corpus'', we achieve state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more. To facilitate future work on transfer learning for NLP, we release our data set, pre-trained models, and code.

PaperPDFCodeCode 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 31 code samples harvested from 8 repositories linked to this paper: 21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 31 samples from 8 repositories, 21 ran (20 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 29 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

google-research/text-to-text-transfer-transformer mentioned in papermentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning (arXiv:2111.10952; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
ArvinZhuang/BiTAG mentioned on GitHubpytorchMITSyntology: 1 sample, 0 ran · 1 unverified report
ChernovAndrey/chronos-forecasting-wasserstein mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Chronos: Learning the Language of Time Series (arXiv:2403.07815; that paper's own run record: 23 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 5 honoured, 1 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
JunnYu/x-transformers-paddle mentioned on GitHubjaxApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Swin Transformer V2: Scaling Up Capacity and Resolution (arXiv:2111.09883; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 3 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report
KAGUYAHONGLAI/SRC mentioned on GitHubtfApache-2.0Syntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
Ki6an/fastT5 mentioned on GitHubpytorchApache-2.0Syntology: 3 samples, 0 ran · 3 unverified report
Nimesh-Patel/text-to-text-transfer-transformer mentioned on GitHubtfApache-2.0Syntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
Sharif-SLPL/t5-fa mentioned on GitHubjaxSyntology: not harvested report
abelriboulot/onnxt5 mentioned on GitHubpytorchApache-2.0Syntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
airc-keti/ke-t5 mentioned on GitHubtfApache-2.0Syntology: not harvested report
allenai/c4-documentation mentioned on GitHubSyntology: not harvested report
allenai/dolma mentioned on GitHubApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research (arXiv:2402.00159; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
amazon-science/chronos-forecasting mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Chronos: Learning the Language of Time Series (arXiv:2403.07815; that paper's own run record: 23 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 5 honoured, 1 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
asahi417/lm-question-generation mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Generative Language Models for Paragraph-Level Question Generation (arXiv:2210.03992; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
asahi417/lmppl mentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to arXiv:2506.15629 (its page on Syntology; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
bayer-science-for-a-better-life/data2text-bioleaflets mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation,... (arXiv:1910.13461; that paper's own run record: 40 ran (of which 7 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 2 violated, 27 with no contract checked; 10 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report
bigscience-workshop/architecture-objective mentioned on GitHubjaxApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot... (arXiv:2204.05832; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
cccntu/ft5-demo mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
cccntu/ft5-demo-space mentioned on GitHubpytorchSyntology: not harvested report
conceptofmind/LaMDA-pytorch 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) and LaMDA: Language Models for Dialog Applications (arXiv:2201.08239; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
conceptofmind/lamda-rlhf-pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LaMDA: Language Models for Dialog Applications (arXiv:2201.08239; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
dawn0815/UniSA mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to UniSA: Unified Generative Framework for Sentiment Analysis (arXiv:2309.01339; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
facebookresearch/atlas mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Atlas: Few-shot Learning with Retrieval Augmented Language Models (arXiv:2208.03299; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
google-research/t5x mentioned on GitHubjaxSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
google-research/t5x_retrieval mentioned on GitHubjaxApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Exploring Dual Encoder Architectures for Question Answering (arXiv:2204.07120; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
google/seqio mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Scaling Up Models and Data with t5x and seqio (arXiv:2203.17189; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
gulucaptain/dynamictrl mentioned on GitHubpytorchSyntology: 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
ibm/graph_ensemble_learning mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AMR Parsing with Action-Pointer Transformer (arXiv:2104.14674; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified) and Ensembling Graph Predictions for AMR Parsing (arXiv:2110.09131; 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); nothing checks that they implement this paper's method. report
itzprashu1/prashant mentioned on GitHubtfApache-2.0Syntology: not harvested report
jongwooko/nash-pruning-official mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Structured Pruning Learns Compact and Accurate Models (arXiv:2204.00408; that paper's own run record: 9 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
junnyu/paddle_t5 mentioned on GitHubpaddleSyntology: not harvested report
lesterpjy/numeric-t5 mentioned on GitHubMITSyntology: not harvested report
luomancs/retriever_reader_for_okvqa mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering (arXiv:2109.04014; that paper's own run record: 3 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; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
qipengguo/p2_webnlg2020 mentioned on GitHubpytorchBSD-3-ClauseSyntology: not harvested report
s-nlp/russe_detox_2022 mentioned on GitHubpytorchSyntology: not harvested report
safakkbilici/Academic-Paper-Title-Recommendation mentioned on GitHubSyntology: not harvested report
shivamraval98/multitask-t5_ae mentioned on GitHubpytorchMITSyntology: 8 samples, 7 ran (0 instrument-failed) · 1 unverified report
skoltech-nlp/russe_detox_2022 mentioned on GitHubpytorchSyntology: not harvested report
thecodemasterk/Text-to-Text-transfer-transformers mentioned on GitHubtfSyntology: not harvested report
thu-keg/omnievent mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ACL Anthology id 2023.findings-acl.586 (that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
thudm/swissarmytransformer mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Prefix-Tuning: Optimizing Continuous Prompts for Generation (arXiv:2101.00190; that paper's own run record: 4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified) and GLM: General Language Model Pretraining with Autoregressive Blank Infilling (arXiv:2103.10360; that paper's own run record: 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); nothing checks that they implement this paper's method. report
um-arm-lab/efficient-eng-2-ltl mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Data-Efficient Learning of Natural Language to Linear Temporal Logic Translators for... (arXiv:2303.08006; that paper's own run record: 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); nothing checks that they implement this paper's method. report
vgaraujov/seq2seq-spanish-plms mentioned on GitHubpytorchSyntology: not harvested report
volcengine/vegiantmodel mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Language Models are Few-Shot Learners (arXiv:2005.14165; that paper's own run record: 45 ran (of which 0 constructed an object rather than computing a result; 37 with no instrument failure: 3 honoured, 2 violated, 32 with no contract checked; 8 where Syntology's instrument failed) · 20 unverified); nothing checks that they implement this paper's method. report
wangcongcong123/ttt mentioned on GitHubpytorchMITSyntology: 7 samples, 6 ran (0 instrument-failed) · 1 unverified report
xuetianci/pacit mentioned on GitHubpytorchSyntology: not harvested report
yizhongw/tk-instruct mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks (arXiv:2204.07705; that paper's own run record: 17 ran (of which 1 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Scaling Instruction-Finetuned Language Models (arXiv:2210.11416; that paper's own run record: 8 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; 7 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method. report
zhiqic/chartreader mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ChartReader: A Unified Framework for Chart Derendering and Comprehension without... (arXiv:2304.02173; that paper's own run record: 16 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 10 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
2023-MindSpore-1/ms-code-164 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code12 mindsporeSyntology: not harvested report
MS-P3/code5 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Instruct-MusicGen: Unlocking Text-to-Music Editing for Music Language Models via... (arXiv:2405.18386; 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) · 0 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
souvikshanku/translit-former pytorchSyntology: 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); nothing checks that they implement this paper's method. report
xiuyu0000/new_papers_codes mindsporeSyntology: not harvested 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

31 samples harvested: 21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 10 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
1ran; the contract check could not run
19ran
10unverified

Licence: 0 of the 31 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 8 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.

ArvinZhuang/BiTAG community (archive-listed) 1 sample, 0 ran · 1 unverified
search_all arxivscraper.py unverified MIT (permissive) · c596c3ab9a0a5e99 · report
KAGUYAHONGLAI/SRC community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
get_eval_metric_values t5/evaluation/eval_utils.py ran Apache-2.0 (permissive) · d372c08056320855 · report fixture: signature events:dict/0/? · returned dict · level recorded 2026-09-24
rouge in 5 papers t5/evaluation/metrics.py ran Apache-2.0 (permissive) · 2189689bfa60b50f · report fixture: signature targets:list/1/str, predictions:list/1/str, score_keys:list/1/str · returned dict · level recorded 2026-09-24
sort_columns t5/evaluation/eval_utils.py ran Apache-2.0 (permissive) · c4b3db3eab3b63b8 · report fixture: signature df:DataFrame/0/?, metric_names:dict/0/? · returned DataFrame · level recorded 2026-09-24
parse_events_files t5/evaluation/eval_utils.py unverified Apache-2.0 (permissive) · 306a70da656ee59e · report
Ki6an/fastT5 community (archive-listed) 3 samples, 0 ran · 3 unverified
create_t5_encoder_decoder fastT5/onnx_exporter.py unverified Apache-2.0 (permissive) · 7060bbb5aee4df3d · report
speed_test in 5 papers fastT5/model_testing_tools.py unverified Apache-2.0 (permissive) · 411f9b71bfd43813 · report
turn_model_into_encoder_decoder fastT5/onnx_exporter.py unverified Apache-2.0 (permissive) · 38d68e317248f579 · report
Nimesh-Patel/text-to-text-transfer-transformer community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
average_tensors t5/transform_checkpoints.py ran Apache-2.0 (permissive) · b628d2dd083dfe70 · report fixture: signature tensors:list/1/Tensor · returned Tensor · level recorded 2026-09-24
main in 235 papers t5/transform_checkpoints.py unverified Apache-2.0 (permissive) · 753651997d048cba · report
abelriboulot/onnxt5 community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
run_embeddings_text onnxt5/api.py ran Apache-2.0 (permissive) · f84ce5dae5cfc6fd · report fixture: signature encoder:MinimalEncoder/0/?, decoder:MinimalDecoder/0/?, tokenizer:MinimalTokenizer/0/?, prompt:str/0/str, max_context_length:int/0/int · returned tuple · level recorded 2026-09-24
top_k_top_p_filtering in 96 papers
census: 8 implementations from 8 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
onnxt5/models.py ran Apache-2.0 (permissive) · bdeda8fda01d8511 · report fixture: signature logits:Tensor/1/float, top_k:int/0/int, top_p:float/0/float, filter_value:float/0/float · returned Tensor · level recorded 2026-09-24
create_t5_encoder_decoder onnxt5/huggingface_utilities.py unverified Apache-2.0 (permissive) · fda9e323d686a1f1 · report
turn_model_into_encoder_decoder onnxt5/huggingface_utilities.py unverified Apache-2.0 (permissive) · 7dabd25c614f61b1 · report
google-research/t5x community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
compute_weighted_accuracy t5x/models.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 24c2125ce6fe13c2 · report fixture: signature logits:ArrayImpl/3/float, targets:ArrayImpl/2/int, weights:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-22
remove_prefix in 26 papers t5x/models.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 61e3339d251a61f7 · report fixture: signature sequence:ArrayImpl/2/int, prefix_length:ArrayImpl/1/int · returned ArrayImpl · level recorded 2026-09-22
shivamraval98/multitask-t5_ae community (archive-listed) 8 samples, 7 ran (0 instrument-failed) · 1 unverified
compute_metric_assert src/t5_eval.py ran fingerprinted MIT (permissive) · 6a636d3c8de90c47 · report fixture: signature labels:ndarray/1/int, predictions:ndarray/1/int · returned dict · level recorded 2026-09-24
compute_metrics in 208 papers src/train_baseline.py ran MIT (permissive) · 6a4d95581e554907 · report fixture: signature pred:SimpleNamespace/0/? · returned dict · level recorded 2026-09-24
load_hf_dataset in 5 papers src/models/T5Model/t5_utils.py ran MIT (permissive) · 189deed085d33fb1 · report fixture: signature data:DataFrame/0/?, tokenizer:MockTokenizer/0/?, args:Args/0/? · returned Dataset · level recorded 2026-09-24
preprocess_batch_for_hf_dataset src/models/T5Model/t5_utils.py ran MIT (permissive) · fcfee7fe0b60418e · report fixture: signature dataset:dict/0/?, tokenizer:MockTokenizer/0/?, args:Args/0/? · returned dict · level recorded 2026-09-24
preprocess_data in 44 papers src/models/T5Model/t5_utils.py ran MIT (permissive) · 2366fa00a16ea6b4 · report fixture: signature data:tuple/1/str · returned tuple · level recorded 2026-09-24
read_df src/t5_eval.py ran MIT (permissive) · 021763e35ac4f976 · report fixture: signature task_type:str/0/str, task_name:str/0/str · returned DataFrame · level recorded 2026-09-24
single_check src/evaluation/eval_ner_t5.py ran fingerprinted MIT (permissive) · aeee04cc3d7f209c · report fixture: signature gold_word:str/0/str, pred_word:str/0/str · returned tuple · level recorded 2026-09-24
compute_metric_ner src/t5_eval.py unverified MIT (permissive) · 0ff1af61d4b10259 · report
wangcongcong123/ttt community (archive-listed) 7 samples, 6 ran (0 instrument-failed) · 1 unverified
dictionize_single_dataset ttt/utils.py ran MIT (permissive) · 4ccab3f2b6762766 · report fixture: signature inputs:tuple/1/dict, tag:str/0/str · returned dict · level recorded 2026-09-24
dictionize_t2t_dataset ttt/utils.py ran MIT (permissive) · 53a850b178e66088 · report fixture: signature train_inputs:tuple/1/dict, eval_inputs:tuple/1/dict · returned dict · level recorded 2026-09-24
get_lr_metric ttt/models.py ran MIT (permissive) · cca53f1f6df7657d · report fixture: signature optimizer:SGD/0/? · returned function · level recorded 2026-09-24
get_scheduler in 122 papers covid_event/finetune_pt.py ran MIT (permissive) · fb8d516be9f13090 · report fixture: signature optimizer:Adam/0/?, scheduler:str/0/str, warmup_steps:int/0/int, num_total:int/0/int · returned LambdaLR · level recorded 2026-09-24
prepare_seq_single_cls_inputs ttt/inputs.py ran MIT (permissive) · 5c3b51a94f35e6cf · report fixture: signature tokenizer:callable/0/?, args:Args/0/?, load_train_num:int/0/int, tokenize_batch_size:NoneType/0/? · returned dict · level recorded 2026-09-24
read_seq_single_cls_examples ttt/inputs.py ran MIT (permissive) · 81b80eb687e95376 · report fixture: signature data_path:str/0/str · returned tuple · level recorded 2026-09-24
convert_seq_single_cls_examples ttt/inputs.py unverified MIT (permissive) · 2f636a05e8e91c3d · report

Tasks

Answer GenerationCommon Sense ReasoningCoreference ResolutionDiversityLinguistic AcceptabilityMachine TranslationMultimodal Intent RecognitionNatural Language InferencePoll GenerationQuestion AnsweringQuestion GenerationSemantic ParsingSemantic Textual SimilaritySentiment AnalysisTransfer LearningWord Sense Disambiguation

Datasets

Introduced by this paper, per the archive.

C4

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Abstractive Text Summarization CNN / Daily Mail T5 ROUGE-1 43.52 #22 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail T5 ROUGE-2 21.55 #22 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail T5 ROUGE-L 40.69 #22 of 53 Archive leaderboard report
Answer Generation WeiboPolls T5 BLEU-1 37.77 #2 of 3 Archive leaderboard report
Answer Generation WeiboPolls T5 BLEU-3 25.86 #2 of 3 Archive leaderboard report
Answer Generation WeiboPolls T5 ROUGE-1 46.20 #2 of 3 Archive leaderboard report
Answer Generation WeiboPolls T5 ROUGE-L 43.32 #2 of 3 Archive leaderboard report
Common Sense Reasoning ReCoRD T5-XXL 11B (fine-tuned) EM 93.4 #6 of 45 Archive leaderboard report
Common Sense Reasoning ReCoRD T5-11B F1 94.1 #36 of 45 Archive leaderboard report
Coreference Resolution Winograd Schema Challenge T5-XXL 11B (fine-tuned) Accuracy 93.8 #7 of 82 Archive leaderboard report
Document Summarization CNN / Daily Mail T5-11B ROUGE-1 43.52 #11 of 26 Archive leaderboard report
Document Summarization CNN / Daily Mail T5-11B ROUGE-2 21.55 #11 of 26 Archive leaderboard report
Document Summarization CNN / Daily Mail T5-11B ROUGE-L 40.69 #11 of 26 Archive leaderboard report
Linguistic Acceptability CoLA T5-11B Accuracy 70.8% #12 of 43 Archive leaderboard report
Linguistic Acceptability CoLA T5-XL 3B Accuracy 67.1% #22 of 43 Archive leaderboard report
Linguistic Acceptability CoLA T5-Large 770M Accuracy 61.2% #28 of 43 Archive leaderboard report
Linguistic Acceptability CoLA T5-Base Accuracy 51.1% #37 of 43 Archive leaderboard report
Linguistic Acceptability CoLA T5-Small Accuracy 41.0% #41 of 43 Archive leaderboard report
Machine Translation WMT2014 English-French T5 BLEU score 43.4 #9 of 57 Archive leaderboard report
Machine Translation WMT2014 English-German T5-11B BLEU score 32.1 #4 of 91 Archive leaderboard report
Machine Translation WMT2014 English-German T5-11B Number of Params 11110M #4 of 91 Archive leaderboard report
Multimodal Intent Recognition PhotoChat T5-3B F1 58.9 #2 of 6 Archive leaderboard report
Multimodal Intent Recognition PhotoChat T5-3B Precision 54.1 #2 of 6 Archive leaderboard report
Multimodal Intent Recognition PhotoChat T5-3B Recall 64.6 #2 of 6 Archive leaderboard report
Multimodal Intent Recognition PhotoChat T5-base F1 58.1 #3 of 6 Archive leaderboard report
Multimodal Intent Recognition PhotoChat T5-base Precision 58.2 #3 of 6 Archive leaderboard report
Multimodal Intent Recognition PhotoChat T5-base Recall 57.9 #3 of 6 Archive leaderboard report
Natural Language Inference CommitmentBank T5-XXL 11B (fine-tuned) Accuracy 96.8 #7 of 20 Archive leaderboard report
Natural Language Inference CommitmentBank T5-XXL 11B (fine-tuned) F1 93.9 #7 of 20 Archive leaderboard report
Natural Language Inference CommitmentBank T5-Large 770M (fine-tuned) Accuracy 94.4 #8 of 20 Archive leaderboard report
Natural Language Inference CommitmentBank T5-Large 770M (fine-tuned) F1 90.3 #8 of 20 Archive leaderboard report
Natural Language Inference CommitmentBank T5-Base 220M (fine-tuned) Accuracy 94 #9 of 20 Archive leaderboard report
Natural Language Inference CommitmentBank T5-Base 220M (fine-tuned) F1 86.2 #9 of 20 Archive leaderboard report
Natural Language Inference MultiNLI T5-XXL 11B (fine-tuned) Matched 92.0 #4 of 67 Archive leaderboard report
Natural Language Inference MultiNLI T5-3B Matched 91.4 #5 of 67 Archive leaderboard report
Natural Language Inference MultiNLI T5-3B Mismatched 91.2 #5 of 67 Archive leaderboard report
Natural Language Inference MultiNLI T5-Large Matched 89.9 #12 of 67 Archive leaderboard report
Natural Language Inference MultiNLI T5-Base Matched 87.1 #23 of 67 Archive leaderboard report
Natural Language Inference MultiNLI T5-Base Mismatched 86.2 #23 of 67 Archive leaderboard report
Natural Language Inference MultiNLI T5-Small Matched 82.4 #38 of 67 Archive leaderboard report
Natural Language Inference MultiNLI T5-Small Mismatched 82.3 #38 of 67 Archive leaderboard report
Natural Language Inference MultiNLI T5-11B Mismatched 91.7 #59 of 67 Archive leaderboard report
Natural Language Inference MultiNLI T5-Large 770M Mismatched 89.6 #61 of 67 Archive leaderboard report
Natural Language Inference QNLI T5-11B Accuracy 96.7% #6 of 43 Archive leaderboard report
Natural Language Inference QNLI T5-3B Accuracy 96.3% #7 of 43 Archive leaderboard report
Natural Language Inference QNLI T5-Large 770M Accuracy 94.8% #12 of 43 Archive leaderboard report
Natural Language Inference QNLI T5-Base Accuracy 93.7% #19 of 43 Archive leaderboard report
Natural Language Inference QNLI T5-Small Accuracy 90.3% #35 of 43 Archive leaderboard report
Natural Language Inference RTE T5-XXL 11B (fine-tuned) Accuracy 92.5% #9 of 90 Archive leaderboard report
Natural Language Inference RTE T5-XL 3B Accuracy 91.1% #14 of 90 Archive leaderboard report
Natural Language Inference RTE T5-Large 770M Accuracy 87.2% #21 of 90 Archive leaderboard report
Natural Language Inference RTE T5-Base 220M Accuracy 80.1% #36 of 90 Archive leaderboard report
Natural Language Inference RTE T5-Small Accuracy 69.9% #54 of 90 Archive leaderboard report
Natural Language Inference WNLI T5-XXL 11B Accuracy 93.2 #3 of 23 Archive leaderboard report
Natural Language Inference WNLI T5-XL 3B Accuracy 89.7 #6 of 23 Archive leaderboard report
Natural Language Inference WNLI T5-Large 770M Accuracy 85.6 #10 of 23 Archive leaderboard report
Natural Language Inference WNLI T5-Base 220M Accuracy 78.8 #12 of 23 Archive leaderboard report
Natural Language Inference WNLI T5-Small 60M Accuracy 69.2 #18 of 23 Archive leaderboard report
Poll Generation WeiboPolls T5 BLEU-1 37.34 #2 of 3 Archive leaderboard report
Poll Generation WeiboPolls T5 BLEU-3 21.06 #2 of 3 Archive leaderboard report
Poll Generation WeiboPolls T5 ROUGE-1 45.33 #2 of 3 Archive leaderboard report
Poll Generation WeiboPolls T5 ROUGE-L 42.69 #2 of 3 Archive leaderboard report
Question Answering BoolQ T5-XXL 11B (fine-tuned) Accuracy 91.2 #5 of 65 Archive leaderboard report
Question Answering BoolQ T5-Large 770M (fine-tuned) Accuracy 85.4 #16 of 65 Archive leaderboard report
Question Answering BoolQ T5-Base 220M (fine-tuned) Accuracy 81.4 #26 of 65 Archive leaderboard report
Question Answering BoolQ T5-Small 60M (fine-tuned) Accuracy 76.4 #33 of 65 Archive leaderboard report
Question Answering COPA T5-XXL 11B (fine-tuned) Accuracy 94.8 #9 of 60 Archive leaderboard report
Question Answering COPA T5-XL 3B (fine-tuned) Accuracy 92 #12 of 60 Archive leaderboard report
Question Answering COPA T5-Large 770M (fine-tuned) Accuracy 83.4 #33 of 60 Archive leaderboard report
Question Answering COPA T5-Base 220M (fine-tuned) Accuracy 71.2 #48 of 60 Archive leaderboard report
Question Answering MultiRC T5-XXL 11B (fine-tuned) F1 88.1 #7 of 30 Archive leaderboard report
Question Answering MultiRC T5-11B EM 63.3 #26 of 30 Archive leaderboard report
Question Answering Quora Question Pairs T5-11B Accuracy 90.4% #4 of 19 Archive leaderboard report
Question Answering Quora Question Pairs T5-Large 770M Accuracy 89.9% #9 of 19 Archive leaderboard report
Question Answering Quora Question Pairs T5-3B Accuracy 89.7% #11 of 19 Archive leaderboard report
Question Answering Quora Question Pairs T5-Base Accuracy 89.4% #12 of 19 Archive leaderboard report
Question Answering Quora Question Pairs T5-Small Accuracy 88.0% #16 of 19 Archive leaderboard report
Question Answering SQuAD1.1 dev T5-11B EM 90.06 #1 of 55 Archive leaderboard report
Question Answering SQuAD1.1 dev T5-11B F1 95.64 #1 of 55 Archive leaderboard report
Question Answering SQuAD1.1 dev T5-3B EM 88.53 #5 of 55 Archive leaderboard report
Question Answering SQuAD1.1 dev T5-3B F1 94.95 #5 of 55 Archive leaderboard report
Question Answering SQuAD1.1 dev T5-Large 770M EM 86.66 #6 of 55 Archive leaderboard report
Question Answering SQuAD1.1 dev T5-Large 770M F1 93.79 #6 of 55 Archive leaderboard report
Question Answering SQuAD1.1 dev T5-Base EM 85.44 #8 of 55 Archive leaderboard report
Question Answering SQuAD1.1 dev T5-Base F1 92.08 #8 of 55 Archive leaderboard report
Question Answering SQuAD1.1 dev T5-Small EM 79.1 #16 of 55 Archive leaderboard report
Question Answering SQuAD1.1 dev T5-Small F1 87.24 #16 of 55 Archive leaderboard report
Question Answering WebQuestions T5.1.1-XXL+SSM EM 42.8 #14 of 37 Archive leaderboard report
Question Generation WeiboPolls T5 BLEU-1 36.91 #2 of 3 Archive leaderboard report
Question Generation WeiboPolls T5 BLEU-3 16.26 #2 of 3 Archive leaderboard report
Question Generation WeiboPolls T5 ROUGE-1 44.46 #2 of 3 Archive leaderboard report
Question Generation WeiboPolls T5 ROUGE-L 42.06 #2 of 3 Archive leaderboard report
Semantic Parsing WebQuestionsSP T5-11B (Raffel et al., 2020) Accuracy 56.5 #5 of 5 Archive leaderboard report
Semantic Textual Similarity MRPC T5-11B Accuracy 90.0% #15 of 45 Archive leaderboard report
Semantic Textual Similarity MRPC T5-11B F1 91.9 #15 of 45 Archive leaderboard report
Semantic Textual Similarity MRPC T5-Large Accuracy 89.9% #16 of 45 Archive leaderboard report
Semantic Textual Similarity MRPC T5-Large F1 92.4 #16 of 45 Archive leaderboard report
Semantic Textual Similarity MRPC T5-3B Accuracy 89.2% #19 of 45 Archive leaderboard report
Semantic Textual Similarity MRPC T5-3B F1 92.5 #19 of 45 Archive leaderboard report
Semantic Textual Similarity MRPC T5-Base Accuracy 87.5% #26 of 45 Archive leaderboard report
Semantic Textual Similarity MRPC T5-Base F1 90.7 #26 of 45 Archive leaderboard report
Semantic Textual Similarity MRPC T5-Small Accuracy 86.6% #32 of 45 Archive leaderboard report
Semantic Textual Similarity MRPC T5-Small F1 89.7 #32 of 45 Archive leaderboard report
Semantic Textual Similarity STS Benchmark T5-11B Pearson Correlation 0.925 #4 of 66 Archive leaderboard report
Semantic Textual Similarity STS Benchmark T5-11B Spearman Correlation 0.921 #4 of 66 Archive leaderboard report
Semantic Textual Similarity STS Benchmark T5-3B Pearson Correlation 0.906 #17 of 66 Archive leaderboard report
Semantic Textual Similarity STS Benchmark T5-3B Spearman Correlation 0.898 #17 of 66 Archive leaderboard report
Semantic Textual Similarity STS Benchmark T5-Large Pearson Correlation 0.899 #20 of 66 Archive leaderboard report
Semantic Textual Similarity STS Benchmark T5-Base Pearson Correlation 0.894 #22 of 66 Archive leaderboard report
Semantic Textual Similarity STS Benchmark T5-Small Pearson Correlation 0.856 #25 of 66 Archive leaderboard report
Semantic Textual Similarity STS Benchmark T5-Small Spearman Correlation 0.85 #25 of 66 Archive leaderboard report
Semantic Textual Similarity STS Benchmark T5-Large 770M Spearman Correlation 0.886 #35 of 66 Archive leaderboard report
Sentiment Analysis SST-2 Binary classification T5-11B Accuracy 97.5 #1 of 87 Archive leaderboard report
Sentiment Analysis SST-2 Binary classification T5-3B Accuracy 97.4 #3 of 87 Archive leaderboard report
Sentiment Analysis SST-2 Binary classification T5-Large 770M Accuracy 96.3 #18 of 87 Archive leaderboard report
Sentiment Analysis SST-2 Binary classification T5-Base Accuracy 95.2 #24 of 87 Archive leaderboard report
Sentiment Analysis SST-2 Binary classification T5-Small Accuracy 91.8 #48 of 87 Archive leaderboard report
Word Sense Disambiguation Words in Context T5-XXL 11B Accuracy 76.9 #8 of 37 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: T5

AdafactorAttentionAttention DropoutBPEDense ConnectionsDropoutGated Linear UnitInverse Square Root ScheduleLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSentencePieceSoftmaxT5

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