Papers › Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks
Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks
Yizhong Wang, Swaroop Mishra, Pegah Alipoormolabashi, Yeganeh Kordi, Amirreza Mirzaei, Anjana Arunkumar, Arjun Ashok, Arut Selvan Dhanasekaran, Atharva Naik, David Stap, Eshaan Pathak, Giannis Karamanolakis, Haizhi Gary Lai, Ishan Purohit, Ishani Mondal, Jacob Anderson, Kirby Kuznia, Krima Doshi, Maitreya Patel, Kuntal Kumar Pal, Mehrad Moradshahi, Mihir Parmar, Mirali Purohit, Neeraj Varshney, Phani Rohitha Kaza, Pulkit Verma, Ravsehaj Singh Puri, Rushang Karia, Shailaja Keyur Sampat, Savan Doshi, Siddhartha Mishra, Sujan Reddy, Sumanta Patro, Tanay Dixit, Xudong Shen, Chitta Baral, Yejin Choi, Noah A. Smith, Hannaneh Hajishirzi, Daniel Khashabi
How well can NLP models generalize to a variety of unseen tasks when provided with task instructions? To address this question, we first introduce Super-NaturalInstructions, a benchmark of 1,616 diverse NLP tasks and their expert-written instructions. Our collection covers 76 distinct task types, including but not limited to classification, extraction, infilling, sequence tagging, text rewriting, and text composition. This large and diverse collection of tasks enables rigorous benchmarking of cross-task generalization under instructions -- training models to follow instructions on a subset of tasks and evaluating them on the remaining unseen ones. Furthermore, we build Tk-Instruct, a transformer model trained to follow a variety of in-context instructions (plain language task definitions or k-shot examples). Our experiments show that Tk-Instruct outperforms existing instruction-following models such as InstructGPT by over 9% on our benchmark despite being an order of magnitude smaller. We further analyze generalization as a function of various scaling parameters, such as the number of observed tasks, the number of instances per task, and model sizes. We hope our dataset and model facilitate future progress towards more general-purpose NLP models.
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):
get_harvested_code_for_paper(arxiv_id="2204.07705")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2204.07705", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2204.07705")
Code
No sample from the archive's official repository (allenai/natural-instructions) is linked to this paper; the 28 samples below come from 6 community repositories. Syntology harvested code from allenai/natural-instructions for another paper.
allenai/natural-instructions: Syntology's graph links these samples to Cross-Task Generalization via Natural Language Crowdsourcing Instructions (arXiv:2104.08773; that paper's own run record: 5 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; 4 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method.
Syntology 28 code samples harvested from 6 repositories linked to this paper: 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. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 28 samples from 6 repositories, 17 ran (15 with no instrument failure; 2 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 1 of its repositories that Syntology harvested for other papers:
- allenai/natural-instructions, official repository: harvested for another paper, listed under the repository
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. 1 of the 17 samples that ran has no recorded date.
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
28 samples harvested: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 4 of the 28 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 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.
dd7ca8d7f3539848 · report
d4d90150a63de630 · report
fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22 59cc5cea5f113a6f · report
fixture: signature x:Tensor/2/float, task_id:int/0/int · returned Tensor · level recorded 2026-09-22 7b12231c5a88204c · report
b95b7688a76ec173 · report
2d44339dc4e6de45 · report
fixture: signature tokenizer:callable/0/?, dataset_path:str/0/str, chat_template:MinimalChatTemplate/0/?, max_sequence_length:int/0/int · returned Dataset · level recorded 2026-09-24 bda36ad0c44dbd74 · report
fixture: signature data:list/1/dict · returned dict · level recorded, date not recorded 308ab826d7562425 · report
fixture: signature template:MessageTemplate/0/?, msg:str/0/str · returned str · level recorded 2026-09-24 b00ec969ab1d91fa · report
fixture: signature prediction:str/0/str, ground_truth:str/0/str, xlingual:bool/0/bool · returned float · level recorded 2026-09-24 ee54d5b1181c1329 · report
fixture: signature model:callable/0/?, tokenizer:callable/0/?, TEMPLATE:MinimalTemplate/0/?, target_dir:str/0/str, device:int/0/int, batch_size:int/0/int · returned dict · level recorded 2026-09-24 302783d5f09f24b0 · report
fixture: signature x:float/0/float, ndigits:int/0/int · returned float · level recorded 2026-09-24 f008f637b646cb1f · report
fixture: signature response_tensors:Tensor/2/int, tokenizer:callable/0/?, strip_strings:list/1/str, max_length:int/0/int · returned tuple · level recorded 2026-09-24 a3ac8409c5a9506e · report
edf1add18a07a762 · report
fixture: signature task_path:str/0/str, sufix:str/0/str · returned list · level recorded 2026-09-24 e168ce39d04b76f1 · report
fixture: signature prediction:str/0/str, ground_truth:str/0/str, xlingual:bool/0/bool · returned bool · level recorded 2026-09-24 9245d1fb6763d365 · report
fixture: signature all_results:dict/0/? · returned float64 · level recorded 2026-09-24 52a9f448d8cbd82a · report
fixture: signature s:str/0/str · returned str · level recorded 2026-09-24 60e0493457ee2cde · report
fixture: signature file_name:str/0/str · returned dict · level recorded 2026-09-24 e7f096a075c4af3c · report
fixture: signature file_name:str/0/str · returned tuple · level recorded 2026-09-24 edfe67269d5fa277 · report
d98382bbc755ff32 · report
fixture: signature arguments:list/1/str, name:str/0/str, value:str/0/str · returned list · level recorded 2026-09-24 588da051624b9d01 · report
fixture: returned Task · level recorded 2026-09-22 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 Tk-INSTRUCT (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for Tk-INSTRUCT (graph method: Tk-INSTRUCT). 2 bricks; individually on a fixture: 0 ran · 2 unverified. The assembly has not been run end-to-end.
one of 3 siblings
- create_task entry · level 0 · unverified ·
d124ae4da8ffcd68 - save_json helper · level 0 · unverified ·
dd7ca8d7f3539848
harvested Assembly for Tk-INSTRUCT (graph method: Tk-INSTRUCT). 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 3 siblings
- Task entry · level 1 · ran ·
588da051624b9d01
harvested Assembly for Tk-INSTRUCT (graph method: Tk-INSTRUCT). 4 bricks; individually on a fixture: 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) · 2 unverified. The assembly has not been run end-to-end.
one of 3 siblings
- AdapterT5 entry · level 0 · unverified ·
7b12231c5a88204c - T5AdapterStack model · level 0 · unverified ·
b95b7688a76ec173 - MixAdapter model · level 1 · ran ·
59cc5cea5f113a6f - Adapter model · level 1 · ran ·
d4d90150a63de630
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="2204.07705") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
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