Papers › PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models

PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models

10 Sep 2021EMNLP 2021 11arXiv:2109.05093archive 2025-07-28

Torsten Scholak, Nathan Schucher, Dzmitry Bahdanau

Large pre-trained language models for textual data have an unconstrained output space; at each decoding step, they can produce any of 10,000s of sub-word tokens. When fine-tuned to target constrained formal languages like SQL, these models often generate invalid code, rendering it unusable. We propose PICARD (code and trained models available at https://github.com/ElementAI/picard), a method for constraining auto-regressive decoders of language models through incremental parsing. PICARD helps to find valid output sequences by rejecting inadmissible tokens at each decoding step. On the challenging Spider and CoSQL text-to-SQL translation tasks, we show that PICARD transforms fine-tuned T5 models with passable performance into state-of-the-art solutions.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 7 code samples harvested from 2 repositories linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 3 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 6 ran (5 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 1 sample from 1 repository, 0 ran (0 with no instrument failure; 0 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:

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ElementAI/picard officialmentioned on GitHubApache-2.0Syntology: 6 samples, 6 ran (1 instrument-failed) · 0 unverified report
servicenow/picard mentioned on GitHubApache-2.0Syntology: 1 sample, 0 ran · 1 unverified report
yangyucheng000/Paper-3 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective... (arXiv:2311.14056; that paper's own run record: 4 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; 0 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

7 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 3 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 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.

3ran · violated contract
1ran · our draft was wrong
2ran
1unverified

Licence: 0 of the 7 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 2 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.

ElementAI/picard official repository 6 samples, 6 ran (1 instrument-failed) · 0 unverified
cosql_get_input seq2seq/utils/cosql.py ran Apache-2.0 (permissive) · 96f7360bd80c6f00 · report fixture: signature utterances:list/1/str, serialized_schema:str/0/str, prefix:str/0/str, sep:str/0/str · returned str · level recorded 2026-09-25
is_commonword in 6 papers seq2seq/utils/bridge_content_encoder.py ran · violated contract Apache-2.0 (permissive) · b724cc2d4066a429 · report fixture: signature s:str/0/str · returned bool · level recorded 2026-09-24
is_number in 70 papers seq2seq/utils/bridge_content_encoder.py ran · violated contract Apache-2.0 (permissive) · f39fdc1ce6cffe08 · report fixture: signature s:str/0/str · returned bool · level recorded 2026-09-24
is_stopword in 8 papers seq2seq/utils/bridge_content_encoder.py ran · violated contract Apache-2.0 (permissive) · d56a1f9221823a48 · report fixture: signature s:str/0/str · returned bool · level recorded 2026-09-24
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
seq2seq/utils/dataset.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 448eab4c7249a72c · report fixture: signature query:str/0/str · returned str · level recorded 2026-09-24
spider_get_input seq2seq/utils/spider.py ran fingerprinted Apache-2.0 (permissive) · b83f0da29c886b71 · report fixture: signature question:str/0/str, serialized_schema:str/0/str, prefix:str/0/str · returned str · level recorded 2026-09-26
servicenow/picard community (archive-listed) 1 sample, 0 ran · 1 unverified
prepare_splits seq2seq/utils/dataset.py unverified Apache-2.0 (permissive) · d3c1fa9d710cc4ff · report

Tasks

Dialogue State TrackingSemantic ParsingText to SQLText-To-SQLTranslation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Dialogue State Tracking CoSQL T5-3B + PICARD interaction match accuracy 23.7 #2 of 9 Archive leaderboard report
Dialogue State Tracking CoSQL T5-3B + PICARD question match accuracy 54.6 #2 of 9 Archive leaderboard report
Semantic Parsing spider T5-3B + PICARD Accuracy 71.9 #5 of 10 Archive leaderboard report
Text-To-SQL SPIDER T5-3B+PICARD Exact Match Accuracy (in Dev) 75.5 #1 of 4 Archive leaderboard report
Text-To-SQL SPIDER T5-3B+PICARD Execution Accuracy (in Dev) 79.3 #1 of 4 Archive leaderboard report
Text-To-SQL SPIDER T5-3B Exact Match Accuracy (in Dev) 71.5 #4 of 4 Archive leaderboard report
Text-To-SQL SPIDER T5-3B Execution Accuracy (in Dev) 74.4 #4 of 4 Archive leaderboard report
Text-To-SQL spider T5-3B + PICARD Exact Match Accuracy (Dev) 75.5 #12 of 20 Archive leaderboard report
Text-To-SQL spider T5-3B + PICARD Exact Match Accuracy (Test) 71.9 #12 of 20 Archive leaderboard report
Text-To-SQL spider T5-3B + PICARD Execution Accuracy (Test) 75.1 #12 of 20 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: PICARD

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