{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/multinli","name":"MultiNLI","full_name":"Multi-Genre Natural Language Inference","description_markdown":"The **Multi-Genre Natural Language Inference** (**MultiNLI**) dataset has 433K sentence pairs. Its size and mode of collection are modeled closely like [SNLI](/dataset/snli). MultiNLI offers ten distinct genres (Face-to-face, Telephone, 9/11, Travel, Letters, Oxford University Press, Slate, Verbatim, Goverment and Fiction) of written and spoken English data. There are matched dev/test sets which are derived from the same sources as those in the training set, and mismatched sets which do not closely resemble any seen at training time.\r\n\r\nSource: [Semantic Sentence Matching with Densely-connectedRecurrent and Co-attentive Information](https://arxiv.org/abs/1805.11360)","description_withheld":null,"homepage":"https://cims.nyu.edu/~sbowman/multinli/","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-broad-coverage-challenge-corpus-for","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","first_author":"Adina Williams","url":null},"license":{"name":"Custom (multiple, see the paper)","url":"https://cims.nyu.edu/~sbowman/multinli/paper.pdf"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"}],"languages":[{"name":"Vietnamese","url":"/datasets/language/vietnamese"}],"variants":["MultiNLI MisMatched dev","MultiNLI Matched dev","MultiNLI Dev MisMatched","MultiNLI Dev Matched","MNLI-mm","mnli_mismatched","MNLI-m","MNLI","MultiNLI-mismatched","MultiNLI-matched","multi_nli","MultiNLI Dev","MultiNLI"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/multi_nli","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/multi_nli_mismatch","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/nyu-mll/multi_nli","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/nyu-mll/multi_nli_mismatch","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#multinli","frameworks":["pytorch"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/multi_nli","frameworks":["tf","jax"]}],"num_papers_in_archive":1830,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/natural-language-inference-on-multinli","task":"Natural Language Inference","dataset_variant":"MultiNLI","rows":67,"metrics":["Matched","Mismatched","Accuracy","Dev Matched","Dev Mismatched"],"first_row_in_archive_order":{"model":"Turing NLR v5 XXL 5.4B (fine-tuned)","paper":null,"metrics":{"Matched":"92.6","Mismatched":"92.4"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/natural-language-inference-on-multinli-dev","task":"Natural Language Inference","dataset_variant":"MultiNLI Dev","rows":10,"metrics":["Matched","Mismatched"],"first_row_in_archive_order":{"model":"TinyBERT-6 67M","paper":"/paper/190910351","metrics":{"Matched":"84.5","Mismatched":"84.5"},"code_links":[{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/tinybert"},{"title":"huawei-noah/Pretrained-Language-Model","url":"https://github.com/huawei-noah/Pretrained-Language-Model/tree/master/TinyBERT"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/nlp/tinybert"},{"title":"mkavim/finetune_bert","url":"https://github.com/mkavim/finetune_bert"},{"title":"MindCode-4/code-5","url":"https://github.com/MindCode-4/code-5/tree/main/tinybert"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/1/tinybert"},{"title":"xiaolilaoli/tiny_bert_ms","url":"https://github.com/xiaolilaoli/tiny_bert_ms"},{"title":"pwc-1/Paper-10","url":"https://github.com/pwc-1/Paper-10/tree/main/tinybert"},{"title":"graison-thomas/TinyFinBERT","url":"https://github.com/graison-thomas/TinyFinBERT"},{"title":"2023-MindSpore-1/ms-code-166","url":"https://github.com/2023-MindSpore-1/ms-code-166"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/natural-language-inference-on-multi-nli","task":"Natural Language Inference","dataset_variant":"multi_nli","rows":0,"metrics":["Accuracy","F1 Macro","F1 Micro","F1 Weighted","Precision Macro","Precision Micro","Precision Weighted","Recall Macro","Recall Micro","Recall Weighted","loss"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-generation-on-mnli","task":"Text Generation","dataset_variant":"MNLI","rows":0,"metrics":["acc"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":40,"of":40,"counts":{"papers_with_a_benchmark_row":40,"with_a_code_link":35,"where_syntology_ran_a_sample":21,"not_listed_spam_title":0,"listed":40,"listed_where_code_ran":21,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":20,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":20,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/first-train-to-generate-then-generate-to","slug":"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","arxiv_id":"2412.09263","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/generative-pretrained-structured-transformers","slug":"generative-pretrained-structured-transformers","title":"Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale","date":"2024-03-13","arxiv_id":"2403.08293","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["ant-research/structuredlm_rtdt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/generative-pretrained-structured-transformers#ran","syntology_url":"https://syntology.ai/paper/2403.08293","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.08293"}}}},{"paper":"/paper/not-all-layers-are-equally-as-important-every","slug":"not-all-layers-are-equally-as-important-every","title":"Not all layers are equally as important: Every Layer Counts BERT","date":"2023-11-03","arxiv_id":"2311.02265","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/lm-cppf-paraphrasing-guided-data-augmentation","slug":"lm-cppf-paraphrasing-guided-data-augmentation","title":"LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning","date":"2023-05-29","arxiv_id":"2305.18169","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/lamini-lm-a-diverse-herd-of-distilled-models","slug":"lamini-lm-a-diverse-herd-of-distilled-models","title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","date":"2023-04-27","arxiv_id":"2304.14402","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/llm-int8-8-bit-matrix-multiplication-for","slug":"llm-int8-8-bit-matrix-multiplication-for","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","date":"2022-08-15","arxiv_id":"2208.07339","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["timdettmers/bitsandbytes"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/llm-int8-8-bit-matrix-multiplication-for#ran","syntology_url":"https://syntology.ai/paper/2208.07339","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.07339"}}}},{"paper":"/paper/adversarial-self-attention-for-language","slug":"adversarial-self-attention-for-language","title":"Adversarial Self-Attention for Language Understanding","date":"2022-06-25","arxiv_id":"2206.12608","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/prune-once-for-all-sparse-pre-trained","slug":"prune-once-for-all-sparse-pre-trained","title":"Prune Once for All: Sparse Pre-Trained Language Models","date":"2021-11-10","arxiv_id":"2111.05754","rows_on_this_dataset":9,"code_links":2,"syntology":null},{"paper":"/paper/charformer-fast-character-transformers-via","slug":"charformer-fast-character-transformers-via","title":"Charformer: Fast Character Transformers via Gradient-based Subword Tokenization","date":"2021-06-23","arxiv_id":"2106.12672","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":7,"samples_constructed":3,"samples_ran_checked":4,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/charformer-fast-character-transformers-via#ran","syntology_url":"https://syntology.ai/paper/2106.12672","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12672"}}}},{"paper":"/paper/pay-attention-to-mlps","slug":"pay-attention-to-mlps","title":"Pay Attention to MLPs","date":"2021-05-17","arxiv_id":"2105.08050","rows_on_this_dataset":1,"code_links":20,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":44,"samples_ran":34,"samples_constructed":15,"samples_ran_checked":31,"samples_ran_instrument_failed":3,"samples_unverified":10,"pointer_only_for_licence":11,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pay-attention-to-mlps#ran","syntology_url":"https://syntology.ai/paper/2105.08050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08050"}}}},{"paper":"/paper/fnet-mixing-tokens-with-fourier-transforms","slug":"fnet-mixing-tokens-with-fourier-transforms","title":"FNet: Mixing Tokens with Fourier Transforms","date":"2021-05-09","arxiv_id":"2105.03824","rows_on_this_dataset":2,"code_links":12,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fnet-mixing-tokens-with-fourier-transforms#ran","syntology_url":"https://syntology.ai/paper/2105.03824","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03824"}}}},{"paper":"/paper/how-to-train-bert-with-an-academic-budget","slug":"how-to-train-bert-with-an-academic-budget","title":"How to Train BERT with an Academic Budget","date":"2021-04-15","arxiv_id":"2104.07705","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/informer-transformer-likes-informed-attention","slug":"informer-transformer-likes-informed-attention","title":"RealFormer: Transformer Likes Residual Attention","date":"2020-12-21","arxiv_id":"2012.11747","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/a-statistical-framework-for-low-bitwidth","slug":"a-statistical-framework-for-low-bitwidth","title":"A Statistical Framework for Low-bitwidth Training of Deep Neural Networks","date":"2020-10-27","arxiv_id":"2010.14298","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":1,"official":{"repos":["cjf00000/StatQuant"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-statistical-framework-for-low-bitwidth#ran","syntology_url":"https://syntology.ai/paper/2010.14298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.14298"}}}},{"paper":"/paper/big-bird-transformers-for-longer-sequences","slug":"big-bird-transformers-for-longer-sequences","title":"Big Bird: Transformers for Longer Sequences","date":"2020-07-28","arxiv_id":"2007.14062","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":10,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":8,"samples_unverified":5,"pointer_only_for_licence":11,"official":{"repos":["google-research/bigbird"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/big-bird-transformers-for-longer-sequences#ran","syntology_url":"https://syntology.ai/paper/2007.14062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.14062"}}}},{"paper":"/paper/squeezebert-what-can-computer-vision-teach","slug":"squeezebert-what-can-computer-vision-teach","title":"SqueezeBERT: What can computer vision teach NLP about efficient neural networks?","date":"2020-06-19","arxiv_id":"2006.11316","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["huggingface/transformers"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/squeezebert-what-can-computer-vision-teach#ran","syntology_url":"https://syntology.ai/paper/2006.11316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11316"}}}},{"paper":"/paper/deberta-decoding-enhanced-bert-with","slug":"deberta-decoding-enhanced-bert-with","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","date":"2020-06-05","arxiv_id":"2006.03654","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":9,"pointer_only_for_licence":3,"official":{"repos":["microsoft/DeBERTa"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","named_in_paper","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deberta-decoding-enhanced-bert-with#ran","syntology_url":"https://syntology.ai/paper/2006.03654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.03654"}}}},{"paper":"/paper/what-do-questions-exactly-ask-mfae-duplicate","slug":"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","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/smart-robust-and-efficient-fine-tuning-for","slug":"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","arxiv_id":"1911.03437","rows_on_this_dataset":6,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["namisan/mt-dnn"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/smart-robust-and-efficient-fine-tuning-for#ran","syntology_url":"https://syntology.ai/paper/1911.03437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03437"}}}},{"paper":"/paper/exploring-the-limits-of-transfer-learning","slug":"exploring-the-limits-of-transfer-learning","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","date":"2019-10-23","arxiv_id":"1910.10683","rows_on_this_dataset":7,"code_links":57,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":31,"samples_ran":21,"samples_constructed":0,"samples_ran_checked":20,"samples_ran_instrument_failed":1,"samples_unverified":10,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/exploring-the-limits-of-transfer-learning#ran","syntology_url":"https://syntology.ai/paper/1910.10683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.10683"}}}},{"paper":"/paper/q8bert-quantized-8bit-bert","slug":"q8bert-quantized-8bit-bert","title":"Q8BERT: Quantized 8Bit BERT","date":"2019-10-14","arxiv_id":"1910.06188","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["intellabs/model-compression-research-package","NervanaSystems/nlp-architect"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/q8bert-quantized-8bit-bert#ran","syntology_url":"https://syntology.ai/paper/1910.06188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.06188"}}}},{"paper":"/paper/albert-a-lite-bert-for-self-supervised","slug":"albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","arxiv_id":"1909.11942","rows_on_this_dataset":1,"code_links":48,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":126,"samples_ran":81,"samples_constructed":17,"samples_ran_checked":56,"samples_ran_instrument_failed":25,"samples_unverified":45,"pointer_only_for_licence":28,"official":{"repos":["google-research/ALBERT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/albert-a-lite-bert-for-self-supervised#ran","syntology_url":"https://syntology.ai/paper/1909.11942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11942"}}}},{"paper":"/paper/190910351","slug":"190910351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","date":"2019-09-23","arxiv_id":"1909.10351","rows_on_this_dataset":3,"code_links":10,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":4,"official":{"repos":["huawei-noah/Pretrained-Language-Model"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/190910351#ran","syntology_url":"https://syntology.ai/paper/1909.10351","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.10351"}}}},{"paper":"/paper/q-bert-hessian-based-ultra-low-precision","slug":"q-bert-hessian-based-ultra-low-precision","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","date":"2019-09-12","arxiv_id":"1909.05840","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/structbert-incorporating-language-structures","slug":"structbert-incorporating-language-structures","title":"StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding","date":"2019-08-13","arxiv_id":"1908.04577","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/ernie-20-a-continual-pre-training-framework","slug":"ernie-20-a-continual-pre-training-framework","title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","date":"2019-07-29","arxiv_id":"1907.12412","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["PaddlePaddle/ERNIE"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ernie-20-a-continual-pre-training-framework#ran","syntology_url":"https://syntology.ai/paper/1907.12412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.12412"}}}},{"paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","slug":"roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","arxiv_id":"1907.11692","rows_on_this_dataset":2,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":48,"samples_ran":37,"samples_constructed":11,"samples_ran_checked":36,"samples_ran_instrument_failed":1,"samples_unverified":11,"pointer_only_for_licence":24,"official":{"repos":["pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/roberta-a-robustly-optimized-bert-pretraining#ran","syntology_url":"https://syntology.ai/paper/1907.11692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11692"}}}},{"paper":"/paper/spanbert-improving-pre-training-by","slug":"spanbert-improving-pre-training-by","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","date":"2019-07-24","arxiv_id":"1907.10529","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":4,"samples_unverified":6,"pointer_only_for_licence":6,"official":{"repos":["facebookresearch/SpanBERT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/spanbert-improving-pre-training-by#ran","syntology_url":"https://syntology.ai/paper/1907.10529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.10529"}}}},{"paper":"/paper/xlnet-generalized-autoregressive-pretraining","slug":"xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","arxiv_id":"1906.08237","rows_on_this_dataset":1,"code_links":27,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":24,"samples_ran":15,"samples_constructed":2,"samples_ran_checked":10,"samples_ran_instrument_failed":5,"samples_unverified":9,"pointer_only_for_licence":4,"official":{"repos":["zihangdai/xlnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/xlnet-generalized-autoregressive-pretraining#ran","syntology_url":"https://syntology.ai/paper/1906.08237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.08237"}}}},{"paper":"/paper/ernie-enhanced-language-representation-with","slug":"ernie-enhanced-language-representation-with","title":"ERNIE: Enhanced Language Representation with Informative Entities","date":"2019-05-17","arxiv_id":"1905.07129","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["thunlp/ERNIE"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ernie-enhanced-language-representation-with#ran","syntology_url":"https://syntology.ai/paper/1905.07129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.07129"}}}},{"paper":"/paper/improving-multi-task-deep-neural-networks-via","slug":"improving-multi-task-deep-neural-networks-via","title":"Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding","date":"2019-04-20","arxiv_id":"1904.09482","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/multi-task-deep-neural-networks-for-natural","slug":"multi-task-deep-neural-networks-for-natural","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","date":"2019-01-31","arxiv_id":"1901.11504","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":5,"samples_unverified":4,"pointer_only_for_licence":4,"official":{"repos":["namisan/mt-dnn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multi-task-deep-neural-networks-for-natural#ran","syntology_url":"https://syntology.ai/paper/1901.11504","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.11504"}}}},{"paper":"/paper/attention-boosted-sequential-inference-model","slug":"attention-boosted-sequential-inference-model","title":"Attention Boosted Sequential Inference Model","date":"2018-12-05","arxiv_id":"1812.01840","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/combining-similarity-features-and-deep","slug":"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","arxiv_id":"1811.00706","rows_on_this_dataset":3,"code_links":3,"syntology":null},{"paper":"/paper/bert-pre-training-of-deep-bidirectional","slug":"bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","arxiv_id":"1810.04805","rows_on_this_dataset":1,"code_links":534,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":659,"samples_ran":300,"samples_constructed":75,"samples_ran_checked":234,"samples_ran_instrument_failed":66,"samples_unverified":359,"pointer_only_for_licence":164,"official":{"repos":["google-research/bert"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bert-pre-training-of-deep-bidirectional#ran","syntology_url":"https://syntology.ai/paper/1810.04805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.04805"}}}},{"paper":"/paper/training-complex-models-with-multi-task-weak","slug":"training-complex-models-with-multi-task-weak","title":"Training Complex Models with Multi-Task Weak Supervision","date":"2018-10-05","arxiv_id":"1810.02840","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-language-understanding-by","slug":"improving-language-understanding-by","title":"Improving Language Understanding by Generative Pre-Training","date":"2018-06-11","arxiv_id":null,"rows_on_this_dataset":1,"code_links":13,"syntology":null},{"paper":"/paper/baseline-needs-more-love-on-simple-word","slug":"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","arxiv_id":"1805.09843","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/glue-a-multi-task-benchmark-and-analysis","slug":"glue-a-multi-task-benchmark-and-analysis","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","date":"2018-04-20","arxiv_id":"1804.07461","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/glue-a-multi-task-benchmark-and-analysis#ran","syntology_url":"https://syntology.ai/paper/1804.07461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.07461"}}}},{"paper":"/paper/learning-general-purpose-distributed-sentence","slug":"learning-general-purpose-distributed-sentence","title":"Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning","date":"2018-03-30","arxiv_id":"1804.00079","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["facebookresearch/SentEval","Maluuba/gensen"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-general-purpose-distributed-sentence#ran","syntology_url":"https://syntology.ai/paper/1804.00079","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.00079"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/first-train-to-generate-then-generate-to","slug":"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","arxiv_id":"2412.09263","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/generative-pretrained-structured-transformers","slug":"generative-pretrained-structured-transformers","title":"Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale","date":"2024-03-13","arxiv_id":"2403.08293","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["ant-research/structuredlm_rtdt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/generative-pretrained-structured-transformers#ran","syntology_url":"https://syntology.ai/paper/2403.08293","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.08293"}}}},{"paper":"/paper/not-all-layers-are-equally-as-important-every","slug":"not-all-layers-are-equally-as-important-every","title":"Not all layers are equally as important: Every Layer Counts BERT","date":"2023-11-03","arxiv_id":"2311.02265","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/lm-cppf-paraphrasing-guided-data-augmentation","slug":"lm-cppf-paraphrasing-guided-data-augmentation","title":"LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning","date":"2023-05-29","arxiv_id":"2305.18169","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/lamini-lm-a-diverse-herd-of-distilled-models","slug":"lamini-lm-a-diverse-herd-of-distilled-models","title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","date":"2023-04-27","arxiv_id":"2304.14402","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/llm-int8-8-bit-matrix-multiplication-for","slug":"llm-int8-8-bit-matrix-multiplication-for","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","date":"2022-08-15","arxiv_id":"2208.07339","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["timdettmers/bitsandbytes"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/llm-int8-8-bit-matrix-multiplication-for#ran","syntology_url":"https://syntology.ai/paper/2208.07339","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.07339"}}}},{"paper":"/paper/adversarial-self-attention-for-language","slug":"adversarial-self-attention-for-language","title":"Adversarial Self-Attention for Language Understanding","date":"2022-06-25","arxiv_id":"2206.12608","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/prune-once-for-all-sparse-pre-trained","slug":"prune-once-for-all-sparse-pre-trained","title":"Prune Once for All: Sparse Pre-Trained Language Models","date":"2021-11-10","arxiv_id":"2111.05754","rows_on_this_dataset":9,"code_links":2,"syntology":null},{"paper":"/paper/charformer-fast-character-transformers-via","slug":"charformer-fast-character-transformers-via","title":"Charformer: Fast Character Transformers via Gradient-based Subword Tokenization","date":"2021-06-23","arxiv_id":"2106.12672","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":7,"samples_constructed":3,"samples_ran_checked":4,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/charformer-fast-character-transformers-via#ran","syntology_url":"https://syntology.ai/paper/2106.12672","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12672"}}}},{"paper":"/paper/pay-attention-to-mlps","slug":"pay-attention-to-mlps","title":"Pay Attention to MLPs","date":"2021-05-17","arxiv_id":"2105.08050","rows_on_this_dataset":1,"code_links":20,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":44,"samples_ran":34,"samples_constructed":15,"samples_ran_checked":31,"samples_ran_instrument_failed":3,"samples_unverified":10,"pointer_only_for_licence":11,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pay-attention-to-mlps#ran","syntology_url":"https://syntology.ai/paper/2105.08050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08050"}}}},{"paper":"/paper/fnet-mixing-tokens-with-fourier-transforms","slug":"fnet-mixing-tokens-with-fourier-transforms","title":"FNet: Mixing Tokens with Fourier Transforms","date":"2021-05-09","arxiv_id":"2105.03824","rows_on_this_dataset":2,"code_links":12,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fnet-mixing-tokens-with-fourier-transforms#ran","syntology_url":"https://syntology.ai/paper/2105.03824","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03824"}}}},{"paper":"/paper/how-to-train-bert-with-an-academic-budget","slug":"how-to-train-bert-with-an-academic-budget","title":"How to Train BERT with an Academic Budget","date":"2021-04-15","arxiv_id":"2104.07705","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/informer-transformer-likes-informed-attention","slug":"informer-transformer-likes-informed-attention","title":"RealFormer: Transformer Likes Residual Attention","date":"2020-12-21","arxiv_id":"2012.11747","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/a-statistical-framework-for-low-bitwidth","slug":"a-statistical-framework-for-low-bitwidth","title":"A Statistical Framework for Low-bitwidth Training of Deep Neural Networks","date":"2020-10-27","arxiv_id":"2010.14298","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":1,"official":{"repos":["cjf00000/StatQuant"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-statistical-framework-for-low-bitwidth#ran","syntology_url":"https://syntology.ai/paper/2010.14298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.14298"}}}},{"paper":"/paper/big-bird-transformers-for-longer-sequences","slug":"big-bird-transformers-for-longer-sequences","title":"Big Bird: Transformers for Longer Sequences","date":"2020-07-28","arxiv_id":"2007.14062","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":10,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":8,"samples_unverified":5,"pointer_only_for_licence":11,"official":{"repos":["google-research/bigbird"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/big-bird-transformers-for-longer-sequences#ran","syntology_url":"https://syntology.ai/paper/2007.14062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.14062"}}}},{"paper":"/paper/squeezebert-what-can-computer-vision-teach","slug":"squeezebert-what-can-computer-vision-teach","title":"SqueezeBERT: What can computer vision teach NLP about efficient neural networks?","date":"2020-06-19","arxiv_id":"2006.11316","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["huggingface/transformers"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/squeezebert-what-can-computer-vision-teach#ran","syntology_url":"https://syntology.ai/paper/2006.11316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11316"}}}},{"paper":"/paper/deberta-decoding-enhanced-bert-with","slug":"deberta-decoding-enhanced-bert-with","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","date":"2020-06-05","arxiv_id":"2006.03654","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":9,"pointer_only_for_licence":3,"official":{"repos":["microsoft/DeBERTa"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","named_in_paper","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deberta-decoding-enhanced-bert-with#ran","syntology_url":"https://syntology.ai/paper/2006.03654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.03654"}}}},{"paper":"/paper/what-do-questions-exactly-ask-mfae-duplicate","slug":"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","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/smart-robust-and-efficient-fine-tuning-for","slug":"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","arxiv_id":"1911.03437","rows_on_this_dataset":6,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["namisan/mt-dnn"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/smart-robust-and-efficient-fine-tuning-for#ran","syntology_url":"https://syntology.ai/paper/1911.03437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03437"}}}},{"paper":"/paper/exploring-the-limits-of-transfer-learning","slug":"exploring-the-limits-of-transfer-learning","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","date":"2019-10-23","arxiv_id":"1910.10683","rows_on_this_dataset":7,"code_links":57,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":31,"samples_ran":21,"samples_constructed":0,"samples_ran_checked":20,"samples_ran_instrument_failed":1,"samples_unverified":10,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/exploring-the-limits-of-transfer-learning#ran","syntology_url":"https://syntology.ai/paper/1910.10683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.10683"}}}},{"paper":"/paper/q8bert-quantized-8bit-bert","slug":"q8bert-quantized-8bit-bert","title":"Q8BERT: Quantized 8Bit BERT","date":"2019-10-14","arxiv_id":"1910.06188","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["intellabs/model-compression-research-package","NervanaSystems/nlp-architect"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/q8bert-quantized-8bit-bert#ran","syntology_url":"https://syntology.ai/paper/1910.06188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.06188"}}}},{"paper":"/paper/albert-a-lite-bert-for-self-supervised","slug":"albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","arxiv_id":"1909.11942","rows_on_this_dataset":1,"code_links":48,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":126,"samples_ran":81,"samples_constructed":17,"samples_ran_checked":56,"samples_ran_instrument_failed":25,"samples_unverified":45,"pointer_only_for_licence":28,"official":{"repos":["google-research/ALBERT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/albert-a-lite-bert-for-self-supervised#ran","syntology_url":"https://syntology.ai/paper/1909.11942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11942"}}}},{"paper":"/paper/190910351","slug":"190910351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","date":"2019-09-23","arxiv_id":"1909.10351","rows_on_this_dataset":3,"code_links":10,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":4,"official":{"repos":["huawei-noah/Pretrained-Language-Model"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/190910351#ran","syntology_url":"https://syntology.ai/paper/1909.10351","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.10351"}}}},{"paper":"/paper/q-bert-hessian-based-ultra-low-precision","slug":"q-bert-hessian-based-ultra-low-precision","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","date":"2019-09-12","arxiv_id":"1909.05840","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/structbert-incorporating-language-structures","slug":"structbert-incorporating-language-structures","title":"StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding","date":"2019-08-13","arxiv_id":"1908.04577","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/ernie-20-a-continual-pre-training-framework","slug":"ernie-20-a-continual-pre-training-framework","title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","date":"2019-07-29","arxiv_id":"1907.12412","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["PaddlePaddle/ERNIE"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ernie-20-a-continual-pre-training-framework#ran","syntology_url":"https://syntology.ai/paper/1907.12412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.12412"}}}},{"paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","slug":"roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","arxiv_id":"1907.11692","rows_on_this_dataset":2,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":48,"samples_ran":37,"samples_constructed":11,"samples_ran_checked":36,"samples_ran_instrument_failed":1,"samples_unverified":11,"pointer_only_for_licence":24,"official":{"repos":["pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/roberta-a-robustly-optimized-bert-pretraining#ran","syntology_url":"https://syntology.ai/paper/1907.11692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11692"}}}},{"paper":"/paper/spanbert-improving-pre-training-by","slug":"spanbert-improving-pre-training-by","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","date":"2019-07-24","arxiv_id":"1907.10529","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":4,"samples_unverified":6,"pointer_only_for_licence":6,"official":{"repos":["facebookresearch/SpanBERT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/spanbert-improving-pre-training-by#ran","syntology_url":"https://syntology.ai/paper/1907.10529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.10529"}}}},{"paper":"/paper/xlnet-generalized-autoregressive-pretraining","slug":"xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","arxiv_id":"1906.08237","rows_on_this_dataset":1,"code_links":27,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":24,"samples_ran":15,"samples_constructed":2,"samples_ran_checked":10,"samples_ran_instrument_failed":5,"samples_unverified":9,"pointer_only_for_licence":4,"official":{"repos":["zihangdai/xlnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/xlnet-generalized-autoregressive-pretraining#ran","syntology_url":"https://syntology.ai/paper/1906.08237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.08237"}}}},{"paper":"/paper/ernie-enhanced-language-representation-with","slug":"ernie-enhanced-language-representation-with","title":"ERNIE: Enhanced Language Representation with Informative Entities","date":"2019-05-17","arxiv_id":"1905.07129","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["thunlp/ERNIE"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ernie-enhanced-language-representation-with#ran","syntology_url":"https://syntology.ai/paper/1905.07129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.07129"}}}},{"paper":"/paper/improving-multi-task-deep-neural-networks-via","slug":"improving-multi-task-deep-neural-networks-via","title":"Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding","date":"2019-04-20","arxiv_id":"1904.09482","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/multi-task-deep-neural-networks-for-natural","slug":"multi-task-deep-neural-networks-for-natural","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","date":"2019-01-31","arxiv_id":"1901.11504","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":5,"samples_unverified":4,"pointer_only_for_licence":4,"official":{"repos":["namisan/mt-dnn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multi-task-deep-neural-networks-for-natural#ran","syntology_url":"https://syntology.ai/paper/1901.11504","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.11504"}}}},{"paper":"/paper/attention-boosted-sequential-inference-model","slug":"attention-boosted-sequential-inference-model","title":"Attention Boosted Sequential Inference Model","date":"2018-12-05","arxiv_id":"1812.01840","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/combining-similarity-features-and-deep","slug":"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","arxiv_id":"1811.00706","rows_on_this_dataset":3,"code_links":3,"syntology":null},{"paper":"/paper/bert-pre-training-of-deep-bidirectional","slug":"bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","arxiv_id":"1810.04805","rows_on_this_dataset":1,"code_links":534,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":659,"samples_ran":300,"samples_constructed":75,"samples_ran_checked":234,"samples_ran_instrument_failed":66,"samples_unverified":359,"pointer_only_for_licence":164,"official":{"repos":["google-research/bert"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bert-pre-training-of-deep-bidirectional#ran","syntology_url":"https://syntology.ai/paper/1810.04805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.04805"}}}},{"paper":"/paper/training-complex-models-with-multi-task-weak","slug":"training-complex-models-with-multi-task-weak","title":"Training Complex Models with Multi-Task Weak Supervision","date":"2018-10-05","arxiv_id":"1810.02840","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-language-understanding-by","slug":"improving-language-understanding-by","title":"Improving Language Understanding by Generative Pre-Training","date":"2018-06-11","arxiv_id":null,"rows_on_this_dataset":1,"code_links":13,"syntology":null},{"paper":"/paper/baseline-needs-more-love-on-simple-word","slug":"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","arxiv_id":"1805.09843","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/glue-a-multi-task-benchmark-and-analysis","slug":"glue-a-multi-task-benchmark-and-analysis","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","date":"2018-04-20","arxiv_id":"1804.07461","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/glue-a-multi-task-benchmark-and-analysis#ran","syntology_url":"https://syntology.ai/paper/1804.07461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.07461"}}}},{"paper":"/paper/learning-general-purpose-distributed-sentence","slug":"learning-general-purpose-distributed-sentence","title":"Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning","date":"2018-03-30","arxiv_id":"1804.00079","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["facebookresearch/SentEval","Maluuba/gensen"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-general-purpose-distributed-sentence#ran","syntology_url":"https://syntology.ai/paper/1804.00079","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.00079"}}}}],"papers_where_code_ran":21,"papers_where_code_ran_first_page":"/dataset/multinli/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/multinli/papers/ran/1","json":"/dataset/multinli/papers/ran/1.json","rows":21}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":23,"samples_harvested":1061,"samples_ran":577,"samples_constructed":126,"samples_ran_checked":442,"samples_ran_instrument_failed":135,"samples_unverified":484,"pointer_only_for_licence":273,"papers_with_no_sample_that_ran":2,"papers_with_a_sample_that_ran":21,"papers_with_a_run_with_no_instrument_failure":20,"papers_where_every_run_was_an_instrument_failure":1,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":20,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/natural-language-inference-on-multinli","since_archive":"/sota/natural-language-inference-on-multinli#since-judged","papers_judged":18,"placed":0},{"leaderboard":"/sota/natural-language-inference-on-multinli-dev","since_archive":"/sota/natural-language-inference-on-multinli-dev#since-judged","papers_judged":3,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"11a94a774d55ed7c110755cb593f44e15a012fcd58e0d112b8af30b9509f863b","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}