{"url":"/dataset/snli","name":"SNLI","full_name":"Stanford Natural Language Inference","description_markdown":"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.\r\n\r\nSource: [Breaking NLI Systemswith Sentences that Require Simple Lexical Inferences](https://arxiv.org/abs/1805.02266)","description_withheld":null,"homepage":"https://nlp.stanford.edu/projects/snli/.","introduced_date":"2015-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-large-annotated-corpus-for-learning-natural","title":"A large annotated corpus for learning natural language inference","first_author":"Samuel R. Bowman","url":null},"license":{"name":"CC BY-SA 4.0","url":"https://creativecommons.org/licenses/by-sa/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["SNLI","JSNLI"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/1-800-SHARED-TASKS/SNLI-NLI","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/snli","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/shibing624/snli-zh","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/stanfordnlp/snli","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Dev372/temp","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/shibing624/nli_zh","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#the-stanford-natural-language-inference-snli-corpus","frameworks":["pytorch"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/snli","frameworks":["tf","jax"]},{"repo":"https://github.com/allenai/allennlp-models","url":"https://docs.allennlp.org/models/main/models/pair_classification/dataset_readers/snli/","frameworks":["pytorch"]}],"num_papers_in_archive":1311,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset_variant":"SNLI","rows":98,"metrics":["% Test Accuracy","% Train Accuracy","Parameters","Dev Accuracy","% Dev Accuracy","Accuracy"],"first_row_in_archive_order":{"model":"UnitedSynT5 (3B)","paper":"/paper/first-train-to-generate-then-generate-to","metrics":{"% Test Accuracy":"94.7"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/first-train-to-generate-then-generate-to","title":"First Train to Generate, then Generate to Train: UnitedSynT5 for Few-Shot NLI","date":"2024-12-12","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/splitee-early-exit-in-deep-neural-networks","title":"SplitEE: Early Exit in Deep Neural Networks with Split Computing","date":"2023-09-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deim-an-effective-deep-encoding-and","title":"DEIM: An effective deep encoding and interaction model for sentence matching","date":"2022-03-20","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/entailment-as-few-shot-learner","title":"Entailment as Few-Shot Learner","date":"2021-04-29","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/self-explaining-structures-improve-nlp-models","title":"Self-Explaining Structures Improve NLP Models","date":"2020-12-03","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/conditionally-adaptive-multi-task-learning","title":"Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data","date":"2020-09-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/what-do-questions-exactly-ask-mfae-duplicate","title":"What Do Questions Exactly Ask? MFAE: Duplicate Question Identification with Multi-Fusion Asking Emphasis","date":"2020-05-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/smart-robust-and-efficient-fine-tuning-for","title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","date":"2019-11-08","rows_on_this_dataset":5,"code_links":6,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":8,"samples_ran":8,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/semantics-aware-bert-for-language","title":"Semantics-aware BERT for Language Understanding","date":"2019-09-05","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":12,"samples_ran":4,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/delta-a-deep-learning-based-language","title":"DELTA: A DEep learning based Language Technology plAtform","date":"2019-08-02","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/simple-and-effective-text-matching-with-1","title":"Simple and Effective Text Matching with Richer Alignment Features","date":"2019-08-01","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/discourse-marker-augmented-network-with-1","title":"Discourse Marker Augmented Network with Reinforcement Learning for Natural Language Inference","date":"2019-07-23","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/star-transformer","title":"Star-Transformer","date":"2019-02-25","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/multi-task-deep-neural-networks-for-natural","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","date":"2019-01-31","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":13,"samples_ran":7,"samples_unverified":6,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/attention-boosted-sequential-inference-model","title":"Attention Boosted Sequential Inference Model","date":"2018-12-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/parameter-re-initialization-through-cyclical","title":"Parameter Re-Initialization through Cyclical Batch Size Schedules","date":"2018-12-04","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/combining-similarity-features-and-deep","title":"Combining Similarity Features and Deep Representation Learning for Stance Detection in the Context of Checking Fake News","date":"2018-11-02","rows_on_this_dataset":3,"code_links":3,"syntology":null},{"paper":"/paper/i-know-what-you-want-semantic-learning-for","title":"Explicit Contextual Semantics for Text Comprehension","date":"2018-09-08","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/cell-aware-stacked-lstms-for-modeling","title":"Cell-aware Stacked LSTMs for Modeling Sentences","date":"2018-09-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/natural-language-inference-with-hierarchical","title":"Sentence Embeddings in NLI with Iterative Refinement Encoders","date":"2018-08-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dynamic-self-attention-computing-attention","title":"Dynamic Self-Attention : Computing Attention over Words Dynamically for Sentence Embedding","date":"2018-08-22","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/multiway-attention-networks-for-modeling","title":"Multiway Attention Networks for Modeling Sentence Pairs","date":"2018-07-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/enhancing-sentence-embedding-with-generalized","title":"Enhancing Sentence Embedding with Generalized Pooling","date":"2018-06-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-language-understanding-by","title":"Improving Language Understanding by Generative Pre-Training","date":"2018-06-11","rows_on_this_dataset":1,"code_links":13,"syntology":null},{"paper":"/paper/semantic-sentence-matching-with-densely","title":"Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Information","date":"2018-05-29","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/baseline-needs-more-love-on-simple-word","title":"Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms","date":"2018-05-24","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/stochastic-answer-networks-for-natural","title":"Stochastic Answer Networks for Natural Language Inference","date":"2018-04-21","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/dynamic-meta-embeddings-for-improved-sentence","title":"Dynamic Meta-Embeddings for Improved Sentence Representations","date":"2018-04-21","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/dr-bilstm-dependent-reading-bidirectional","title":"DR-BiLSTM: Dependent Reading Bidirectional LSTM for Natural Language Inference","date":"2018-02-15","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/deep-contextualized-word-representations","title":"Deep contextualized word representations","date":"2018-02-15","rows_on_this_dataset":2,"code_links":46,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":58,"samples_ran":24,"samples_unverified":34,"pointer_only_for_licence":25,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/reinforced-self-attention-network-a-hybrid-of","title":"Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling","date":"2018-01-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/compare-compress-and-propagate-enhancing","title":"Compare, Compress and Propagate: Enhancing Neural Architectures with Alignment Factorization for Natural Language Inference","date":"2017-12-30","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/distance-based-self-attention-network-for","title":"Distance-based Self-Attention Network for Natural Language Inference","date":"2017-12-06","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/neural-natural-language-inference-models","title":"Neural Natural Language Inference Models Enhanced with External Knowledge","date":"2017-11-12","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/disan-directional-self-attention-network-for","title":"DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding","date":"2017-09-14","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/natural-language-inference-over-interaction-1","title":"Natural Language Inference over Interaction Space","date":"2017-09-13","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/shortcut-stacked-sentence-encoders-for-multi","title":"Shortcut-Stacked Sentence Encoders for Multi-Domain Inference","date":"2017-08-07","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/recurrent-neural-network-based-sentence","title":"Recurrent Neural Network-Based Sentence Encoder with Gated Attention for Natural Language Inference","date":"2017-08-04","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/learned-in-translation-contextualized-word","title":"Learned in Translation: Contextualized Word Vectors","date":"2017-08-01","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-to-compose-task-specific-tree","title":"Learning to Compose Task-Specific Tree Structures","date":"2017-07-10","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/supervised-learning-of-universal-sentence","title":"Supervised Learning of Universal Sentence Representations from Natural Language Inference Data","date":"2017-05-05","rows_on_this_dataset":1,"code_links":23,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":7,"samples_ran":6,"samples_unverified":1,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bilateral-multi-perspective-matching-for","title":"Bilateral Multi-Perspective Matching for Natural Language Sentences","date":"2017-02-13","rows_on_this_dataset":2,"code_links":10,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/reading-and-thinking-re-read-lstm-unit-for","title":"Reading and Thinking: Re-read LSTM Unit for Textual Entailment Recognition","date":"2016-12-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/enhanced-lstm-for-natural-language-inference","title":"Enhanced LSTM for Natural Language Inference","date":"2016-09-20","rows_on_this_dataset":2,"code_links":12,"syntology":null},{"paper":"/paper/deep-fusion-lstms-for-text-semantic-matching","title":"Deep Fusion LSTMs for Text Semantic Matching","date":"2016-08-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/neural-tree-indexers-for-text-understanding","title":"Neural Tree Indexers for Text Understanding","date":"2016-07-15","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/neural-semantic-encoders","title":"Neural Semantic Encoders","date":"2016-07-14","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/a-decomposable-attention-model-for-natural","title":"A Decomposable Attention Model for Natural Language Inference","date":"2016-06-06","rows_on_this_dataset":4,"code_links":10,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-natural-language-inference-using","title":"Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention","date":"2016-05-30","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/modelling-interaction-of-sentence-pair-with","title":"Modelling Interaction of Sentence Pair with coupled-LSTMs","date":"2016-05-18","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-fast-unified-model-for-parsing-and-sentence","title":"A Fast Unified Model for Parsing and Sentence Understanding","date":"2016-03-19","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/long-short-term-memory-networks-for-machine","title":"Long Short-Term Memory-Networks for Machine Reading","date":"2016-01-25","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-natural-language-inference-with-lstm","title":"Learning Natural Language Inference with LSTM","date":"2015-12-30","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/natural-language-inference-by-tree-based","title":"Natural Language Inference by Tree-Based Convolution and Heuristic Matching","date":"2015-12-28","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/order-embeddings-of-images-and-language","title":"Order-Embeddings of Images and Language","date":"2015-11-19","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/reasoning-about-entailment-with-neural","title":"Reasoning about Entailment with Neural Attention","date":"2015-09-22","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-large-annotated-corpus-for-learning-natural","title":"A large annotated corpus for learning natural language inference","date":"2015-08-21","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":17,"samples_harvested":130,"samples_ran":63,"samples_unverified":67,"pointer_only_for_licence":45,"papers_with_no_sample_that_ran":3,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}