Papers › A Logic-Driven Framework for Consistency of Neural Models

A Logic-Driven Framework for Consistency of Neural Models

31 Aug 2019IJCNLP 2019 11arXiv:1909.00126archive 2025-07-28

Tao Li, Vivek Gupta, Maitrey Mehta, Vivek Srikumar

While neural models show remarkable accuracy on individual predictions, their internal beliefs can be inconsistent across examples. In this paper, we formalize such inconsistency as a generalization of prediction error. We propose a learning framework for constraining models using logic rules to regularize them away from inconsistency. Our framework can leverage both labeled and unlabeled examples and is directly compatible with off-the-shelf learning schemes without model redesign. We instantiate our framework on natural language inference, where experiments show that enforcing invariants stated in logic can help make the predictions of neural models both accurate and consistent.

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 10 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 10 samples from 1 repository, 8 ran (8 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.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

utahnlp/consistency officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 10 samples, 8 ran (0 instrument-failed) · 2 unverified 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.

Code Syntology ran Syntology

10 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 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.

2ran · honoured contract
6ran
2unverified

Licence: 2 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from utahnlp/consistency. “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.

utahnlp/consistency official repository 10 samples, 8 ran (0 instrument-failed) · 2 unverified
get_confusion_matrix in 14 papers confusion_table.py ran Apache-2.0 (permissive) · 123846fe86b24e7f · report fixture: signature left:list/1/int, right:list/1/int, labels:list/1/int · returned list · level recorded 2026-09-25
get_confusion_ratio confusion_table.py ran Apache-2.0 (permissive) · 7e87c334bb7df236 · report fixture: signature mat:list/1/list · returned list · level recorded 2026-09-25
get_glove_words extra_preprocess.py ran Apache-2.0 (permissive) · 02f680c0cdae0af1 · report fixture: signature f:str/0/str · returned set · level recorded 2026-09-25
load in 392 papers confusion_table.py ran Apache-2.0 (permissive) · 9cd88edf7b072d2d · report fixture: signature path:str/0/str · returned list · level recorded 2026-09-25
make_vocab in 5 papers extra_preprocess.py ran Apache-2.0 (permissive) · 05c8b6f42e3dc2fb · report fixture: signature opt:dict/0/?, glove_vocab:set/0/?, word_indexer:MockWordIndexer/0/?, all_word_indexer:MockWordIndexer/0/?, label_indexer:MockLabelIndexer/0/?, sent1:list/1/str, sent2:list/1/str, label:list/1/str, max_seq_l:int/0/int, count:dict/0/? · returned int · level recorded 2026-09-25
pad in 85 papers extra_preprocess.py ran Apache-2.0 (permissive) · da8e4408c385c601 · report fixture: signature ls:list/1/int, length:int/0/int, symbol:int/0/int, pad_back:bool/0/bool · returned list · level recorded 2026-09-25
warmup_constant in 30 papers bert_adam.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 59e4e730a9dc5dc6 · report fixture: signature x:float/0/float, warmup:float/0/float · returned float · level recorded 2026-09-26
warmup_linear in 45 papers bert_adam.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · e0960afdb0d64aa7 · report fixture: signature x:float/0/float, warmup:float/0/float · returned float · level recorded 2026-09-22
load_pipeline cache_bert_batch.py unverified Apache-2.0 (permissive) · 34fb8d968db79ca7 · report
warmup_cosine in 30 papers bert_adam.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 35f7cddf90dd05d4 · report

Tasks

Natural Language Inference

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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