</> Code with Papers by Syntology

Datasets › SNLI

SNLI (Stanford Natural Language Inference)

Introduced by Samuel R. Bowman et al. in A large annotated corpus for learning natural language inference1 Jan 2015 archive 2025-07-28

The SNLI dataset (Stanford Natural Language Inference) consists of 570k sentence-pairs manually labeled as entailment, contradiction, and neutral. Premises are image captions from Flickr30k, while hypotheses were generated by crowd-sourced annotators who were shown a premise and asked to generate entailing, contradicting, and neutral sentences. Annotators were instructed to judge the relation between sentences given that they describe the same event. Each pair is labeled as “entailment”, “neutral”, “contradiction” or “-”, where “-” indicates that an agreement could not be reached.

Source: Breaking NLI Systemswith Sentences that Require Simple Lexical Inferences

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Natural Language Inference SNLI UnitedSynT5 (3B) % Test Accuracy 94.7 First Train to Generate, then Generate to Train:... — 98 Compare

Papers archive 2025-07-28

30 shown of 57 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 1,311. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
First Train to Generate, then Generate to Train: UnitedSynT5 for Few-Shot NLI 0 2 12 Dec 2024 not harvested
SplitEE: Early Exit in Deep Neural Networks with Split Computing 1 1 17 Sep 2023 not harvested
DEIM: An effective deep encoding and interaction model for sentence matching 0 1 20 Mar 2022 not harvested
Entailment as Few-Shot Learner 3 2 29 Apr 2021 ran 1 of 3 samples (2 unverified)
Self-Explaining Structures Improve NLP Models 1 2 3 Dec 2020 not harvested
Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data 1 1 19 Sep 2020 not harvested
What Do Questions Exactly Ask? MFAE: Duplicate Question Identification with Multi-Fusion Asking Emphasis 1 1 7 May 2020 not harvested
SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization 6 5 8 Nov 2019 ran 6 of 8 samples (2 unverified; 1 pointer-only for licence)
Semantics-aware BERT for Language Understanding 1 1 5 Sep 2019 ran 4 of 12 samples (8 unverified)
DELTA: A DEep learning based Language Technology plAtform 2 1 2 Aug 2019 not harvested
Simple and Effective Text Matching with Richer Alignment Features 3 1 1 Aug 2019 ran 1 of 1 samples (0 unverified)
Discourse Marker Augmented Network with Reinforcement Learning for Natural Language Inference 1 2 23 Jul 2019 not harvested
Star-Transformer 2 1 25 Feb 2019 ran 0 of 1 samples (1 unverified)
Multi-Task Deep Neural Networks for Natural Language Understanding 7 2 31 Jan 2019 ran 5 of 13 samples (8 unverified; 2 pointer-only for licence)
Attention Boosted Sequential Inference Model 0 1 5 Dec 2018 not harvested
Parameter Re-Initialization through Cyclical Batch Size Schedules 0 1 4 Dec 2018 not harvested
Combining Similarity Features and Deep Representation Learning for Stance Detection in the Context of Checking Fake News 3 3 2 Nov 2018 not harvested
Explicit Contextual Semantics for Text Comprehension 0 2 8 Sep 2018 not harvested
Cell-aware Stacked LSTMs for Modeling Sentences 0 1 7 Sep 2018 not harvested
Sentence Embeddings in NLI with Iterative Refinement Encoders 1 1 27 Aug 2018 not harvested
Dynamic Self-Attention : Computing Attention over Words Dynamically for Sentence Embedding 1 2 22 Aug 2018 not harvested
Multiway Attention Networks for Modeling Sentence Pairs 1 2 1 Jul 2018 not harvested
Enhancing Sentence Embedding with Generalized Pooling 1 1 26 Jun 2018 not harvested
Improving Language Understanding by Generative Pre-Training 13 1 11 Jun 2018 not harvested
Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Information 0 3 29 May 2018 not harvested
Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms 2 1 24 May 2018 not harvested
Stochastic Answer Networks for Natural Language Inference 3 1 21 Apr 2018 not harvested
Dynamic Meta-Embeddings for Improved Sentence Representations 3 1 21 Apr 2018 not harvested
DR-BiLSTM: Dependent Reading Bidirectional LSTM for Natural Language Inference 0 2 15 Feb 2018 not harvested
Deep contextualized word representations 46 2 15 Feb 2018 ran 23 of 58 samples (35 unverified; 25 pointer-only for licence)

The full list of 57 is in the JSON twin.

Dataset loaders archive 2025-07-28

huggingface.co/datasets/1-800-SHARED-TASKS/SNLI-NLIhuggingface/datasetstfpytorchjax
huggingface.co/datasets/snlihuggingface/datasetstfpytorchjax
huggingface.co/datasets/shibing624/snli-zhhuggingface/datasetstfpytorchjax
huggingface.co/datasets/stanfordnlp/snlihuggingface/datasetstfpytorchjax
huggingface.co/datasets/Dev372/temphuggingface/datasetstfpytorchjax
huggingface.co/datasets/shibing624/nli_zhhuggingface/datasetstfpytorchjax
parl.ai/docs/tasks.html#the-stanford-natural-language-inference-snli-corpusfacebookresearch/ParlAIpytorch
www.tensorflow.org/datasets/catalog/snlitensorflow/datasetstfjax
docs.allennlp.org/models/main/models/pair_classification/dataset_readers/snli/allenai/allennlp-modelspytorch

9 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Natural Language Inference

License archive 2025-07-28

CC BY-SA 4.0

Modalities archive 2025-07-28

Texts

Languages archive 2025-07-28

English

Variants archive 2025-07-28

  • SNLI
  • JSNLI

2 variant names, as the archive lists them.

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