{"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":"/task/linguistic-acceptability","name":"Linguistic Acceptability","slug":"linguistic-acceptability","description_markdown":"Linguistic Acceptability is the task of determining whether a sentence is grammatical or ungrammatical.\r\n\r\nImage Source: [Warstadt et al](https://arxiv.org/pdf/1901.03438v4.pdf)","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":72,"papers_with_code":49,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":5,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/linguistic-acceptability-on-cola","slug":"linguistic-acceptability-on-cola","dataset":"CoLA","dataset_url":"/dataset/cola","rows_in_archive":43,"metrics":["Accuracy","MCC"],"first_row_in_archive_order":{"model":"En-BERT + TDA + PCA","paper_title":"Acceptability Judgements via Examining the Topology of Attention Maps","paper_url":"/paper/acceptability-judgements-via-examining-the","paper_date":"2022-05-19","arxiv_id":"2205.09630","code_links":[{"title":"danchern97/tda4la","url":"https://github.com/danchern97/tda4la"}],"syntology":null}},{"leaderboard":"/sota/linguistic-acceptability-on-rucola","slug":"linguistic-acceptability-on-rucola","dataset":"RuCoLA","dataset_url":"/dataset/rucola","rows_in_archive":9,"metrics":["MCC","Accuracy"],"first_row_in_archive_order":{"model":"Ru-RoBERTa+TDA","paper_title":"Can BERT eat RuCoLA? Topological Data Analysis to Explain","paper_url":"/paper/can-bert-eat-rucola-topological-data-analysis","paper_date":"2023-04-04","arxiv_id":"2304.01680","code_links":[{"title":"upunaprosk/la-tda","url":"https://github.com/upunaprosk/la-tda/blob/master/5_Head_importance.ipynb"},{"title":"upunaprosk/la-tda","url":"https://github.com/upunaprosk/la-tda"}],"syntology":null}},{"leaderboard":"/sota/linguistic-acceptability-on-cola-dev","slug":"linguistic-acceptability-on-cola-dev","dataset":"CoLA Dev","dataset_url":"/dataset/cola","rows_in_archive":6,"metrics":["Accuracy","MCC"],"first_row_in_archive_order":{"model":"En-BERT + TDA","paper_title":"Acceptability Judgements via Examining the Topology of Attention Maps","paper_url":"/paper/acceptability-judgements-via-examining-the","paper_date":"2022-05-19","arxiv_id":"2205.09630","code_links":[{"title":"danchern97/tda4la","url":"https://github.com/danchern97/tda4la"}],"syntology":null}},{"leaderboard":"/sota/linguistic-acceptability-on-itacola","slug":"linguistic-acceptability-on-itacola","dataset":"ItaCoLA","dataset_url":"/dataset/itacola","rows_in_archive":4,"metrics":["MCC","Accuracy"],"first_row_in_archive_order":{"model":"XLM-R + TDA","paper_title":"Acceptability Judgements via Examining the Topology of Attention Maps","paper_url":"/paper/acceptability-judgements-via-examining-the","paper_date":"2022-05-19","arxiv_id":"2205.09630","code_links":[{"title":"danchern97/tda4la","url":"https://github.com/danchern97/tda4la"}],"syntology":null}},{"leaderboard":"/sota/linguistic-acceptability-on-dalaj","slug":"linguistic-acceptability-on-dalaj","dataset":"DaLAJ","dataset_url":"/dataset/dalaj","rows_in_archive":1,"metrics":["Accuracy","MCC"],"first_row_in_archive_order":{"model":"Sw-BERT + H0M","paper_title":"Acceptability Judgements via Examining the Topology of Attention Maps","paper_url":"/paper/acceptability-judgements-via-examining-the","paper_date":"2022-05-19","arxiv_id":"2205.09630","code_links":[{"title":"danchern97/tda4la","url":"https://github.com/danchern97/tda4la"}],"syntology":null}}],"datasets":[{"url":"/dataset/glue","name":"GLUE","full_name":"General Language Understanding Evaluation benchmark","num_papers_in_archive":3197},{"url":"/dataset/cola","name":"CoLA","full_name":"Corpus of Linguistic Acceptability","num_papers_in_archive":710},{"url":"/dataset/dalaj","name":"DaLAJ","full_name":"","num_papers_in_archive":6},{"url":"/dataset/itacola","name":"ItaCoLA","full_name":"","num_papers_in_archive":5},{"url":"/dataset/rucola","name":"RuCoLA","full_name":"","num_papers_in_archive":5}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":72,"of":72,"of_with_code":49,"tagged_in_all":72,"counts":{"archive_papers_tagged":72,"with_a_code_link":49,"where_syntology_ran_a_sample":29,"not_listed_spam_title":0,"listed":72,"listed_where_code_ran":29,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":24,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":24,"listed_every_run_a_failure_of_syntologys_instrument":5,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/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","repositories_listed":534,"syntology":{"n":659,"n_ran":300,"n_constructed":75,"n_ran_checked":234,"n_instrument":66,"n_unverified":359,"n_honours":18,"n_violates":5,"n_no_contract":211,"n_pointer_only":164,"phrase":"300 ran (of which 75 constructed an object rather than computing a result; 234 with no instrument failure: 18 honoured, 5 violated, 211 with no contract checked; 66 where Syntology's instrument failed) · 359 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":67,"syntology":{"n":48,"n_ran":37,"n_constructed":11,"n_ran_checked":36,"n_instrument":1,"n_unverified":11,"n_honours":2,"n_violates":0,"n_no_contract":34,"n_pointer_only":24,"phrase":"37 ran (of which 11 constructed an object rather than computing a result; 36 with no instrument failure: 2 honoured, 0 violated, 34 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":57,"syntology":{"n":31,"n_ran":21,"n_constructed":0,"n_ran_checked":20,"n_instrument":1,"n_unverified":10,"n_honours":1,"n_violates":0,"n_no_contract":19,"n_pointer_only":0,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified","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"}},"official":null}},{"url":"/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","repositories_listed":48,"syntology":{"n":126,"n_ran":81,"n_constructed":17,"n_ran_checked":56,"n_instrument":25,"n_unverified":45,"n_honours":4,"n_violates":0,"n_no_contract":52,"n_pointer_only":28,"phrase":"81 ran (of which 17 constructed an object rather than computing a result; 56 with no instrument failure: 4 honoured, 0 violated, 52 with no contract checked; 25 where Syntology's instrument failed) · 45 unverified","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"}},"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"]}}},{"url":"/paper/distilbert-a-distilled-version-of-bert","slug":"distilbert-a-distilled-version-of-bert","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","date":"2019-10-02","arxiv_id":"1910.01108","repositories_listed":37,"syntology":{"n":27,"n_ran":21,"n_constructed":5,"n_ran_checked":12,"n_instrument":9,"n_unverified":6,"n_honours":3,"n_violates":1,"n_no_contract":8,"n_pointer_only":2,"phrase":"21 ran (of which 5 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 1 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/distilbert-a-distilled-version-of-bert#ran","syntology_url":"https://syntology.ai/paper/1910.01108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.01108"}},"official":{"repos":["huggingface/swift-coreml-transformers","huggingface/transformers"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/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","repositories_listed":14,"syntology":{"n":15,"n_ran":10,"n_constructed":1,"n_ran_checked":2,"n_instrument":8,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":11,"phrase":"10 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":14,"syntology":{"n":13,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":9,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","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"}},"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"]}}},{"url":"/paper/data2vec-a-general-framework-for-self-1","slug":"data2vec-a-general-framework-for-self-1","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","date":"2022-02-07","arxiv_id":"2202.03555","repositories_listed":12,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/data2vec-a-general-framework-for-self-1#ran","syntology_url":"https://syntology.ai/paper/2202.03555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.03555"}},"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"]}}},{"url":"/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","repositories_listed":12,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/paper/190910351","slug":"190910351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","date":"2019-09-23","arxiv_id":"1909.10351","repositories_listed":10,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"0 ran · 4 unverified","sample_list":"/paper/190910351#ran","syntology_url":"https://syntology.ai/paper/1909.10351","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.10351"}},"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":[]}}},{"url":"/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","repositories_listed":7,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":6,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":6,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/paper/pseudolikelihood-reranking-with-masked","slug":"pseudolikelihood-reranking-with-masked","title":"Masked Language Model Scoring","date":"2019-10-31","arxiv_id":"1910.14659","repositories_listed":6,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pseudolikelihood-reranking-with-masked#ran","syntology_url":"https://syntology.ai/paper/1910.14659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.14659"}},"official":{"repos":["awslabs/mlm-scoring"],"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"]}}},{"url":"/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","repositories_listed":6,"syntology":{"n":15,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":5,"syntology":null},{"url":"/paper/q8bert-quantized-8bit-bert","slug":"q8bert-quantized-8bit-bert","title":"Q8BERT: Quantized 8Bit BERT","date":"2019-10-14","arxiv_id":"1910.06188","repositories_listed":5,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":4,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":4,"syntology":null},{"url":"/paper/entailment-as-few-shot-learner","slug":"entailment-as-few-shot-learner","title":"Entailment as Few-Shot Learner","date":"2021-04-29","arxiv_id":"2104.14690","repositories_listed":3,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/entailment-as-few-shot-learner#ran","syntology_url":"https://syntology.ai/paper/2104.14690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14690"}},"official":null}},{"url":"/paper/gedi-generative-discriminator-guided-sequence","slug":"gedi-generative-discriminator-guided-sequence","title":"GeDi: Generative Discriminator Guided Sequence Generation","date":"2020-09-14","arxiv_id":"2009.06367","repositories_listed":3,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/gedi-generative-discriminator-guided-sequence#ran","syntology_url":"https://syntology.ai/paper/2009.06367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.06367"}},"official":{"repos":["salesforce/GeDi"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"url":"/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","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","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"}},"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":[]}}},{"url":"/paper/jcola-japanese-corpus-of-linguistic","slug":"jcola-japanese-corpus-of-linguistic","title":"JCoLA: Japanese Corpus of Linguistic Acceptability","date":"2023-09-22","arxiv_id":"2309.12676","repositories_listed":2,"syntology":null},{"url":"/paper/can-bert-eat-rucola-topological-data-analysis","slug":"can-bert-eat-rucola-topological-data-analysis","title":"Can BERT eat RuCoLA? Topological Data Analysis to Explain","date":"2023-04-04","arxiv_id":"2304.01680","repositories_listed":2,"syntology":null},{"url":"/paper/scandeval-a-benchmark-for-scandinavian","slug":"scandeval-a-benchmark-for-scandinavian","title":"ScandEval: A Benchmark for Scandinavian Natural Language Processing","date":"2023-04-03","arxiv_id":"2304.00906","repositories_listed":2,"syntology":null},{"url":"/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","repositories_listed":2,"syntology":{"n":10,"n_ran":7,"n_constructed":3,"n_ran_checked":4,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":2,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/paper/neural-network-acceptability-judgments","slug":"neural-network-acceptability-judgments","title":"Neural Network Acceptability Judgments","date":"2018-05-31","arxiv_id":"1805.12471","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/neural-network-acceptability-judgments#ran","syntology_url":"https://syntology.ai/paper/1805.12471","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.12471"}},"official":null}},{"url":"/paper/fietje-an-open-efficient-llm-for-dutch","slug":"fietje-an-open-efficient-llm-for-dutch","title":"Fietje: An open, efficient LLM for Dutch","date":"2024-12-19","arxiv_id":"2412.15450","repositories_listed":1,"syntology":null},{"url":"/paper/mela-multilingual-evaluation-of-linguistic","slug":"mela-multilingual-evaluation-of-linguistic","title":"MELA: Multilingual Evaluation of Linguistic Acceptability","date":"2023-11-15","arxiv_id":"2311.09033","repositories_listed":1,"syntology":null},{"url":"/paper/nocola-the-norwegian-corpus-of-linguistic","slug":"nocola-the-norwegian-corpus-of-linguistic","title":"NoCoLA: The Norwegian Corpus of Linguistic Acceptability","date":"2023-06-13","arxiv_id":"2306.07790","repositories_listed":1,"syntology":null},{"url":"/paper/cue-an-uncertainty-interpretation-framework","slug":"cue-an-uncertainty-interpretation-framework","title":"CUE: An Uncertainty Interpretation Framework for Text Classifiers Built on Pre-Trained Language Models","date":"2023-06-06","arxiv_id":"2306.03598","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-acceptability-judgements","slug":"revisiting-acceptability-judgements","title":"Revisiting Acceptability Judgements","date":"2023-05-23","arxiv_id":"2305.14091","repositories_listed":1,"syntology":null},{"url":"/paper/chatgpt-jack-of-all-trades-master-of-none","slug":"chatgpt-jack-of-all-trades-master-of-none","title":"ChatGPT: Jack of all trades, master of none","date":"2023-02-21","arxiv_id":"2302.10724","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/chatgpt-jack-of-all-trades-master-of-none#ran","syntology_url":"https://syntology.ai/paper/2302.10724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.10724"}},"official":{"repos":["clarin-pl/chatgpt-evaluation-01-2023"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/texttt-tasksource-structured-dataset","slug":"texttt-tasksource-structured-dataset","title":"tasksource: A Dataset Harmonization Framework for Streamlined NLP Multi-Task Learning and Evaluation","date":"2023-01-14","arxiv_id":"2301.05948","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/texttt-tasksource-structured-dataset#ran","syntology_url":"https://syntology.ai/paper/2301.05948","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.05948"}},"official":{"repos":["sileod/tasksource"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/rucola-russian-corpus-of-linguistic","slug":"rucola-russian-corpus-of-linguistic","title":"RuCoLA: Russian Corpus of Linguistic Acceptability","date":"2022-10-23","arxiv_id":"2210.12814","repositories_listed":1,"syntology":null},{"url":"/paper/acceptability-judgements-via-examining-the","slug":"acceptability-judgements-via-examining-the","title":"Acceptability Judgements via Examining the Topology of Attention Maps","date":"2022-05-19","arxiv_id":"2205.09630","repositories_listed":1,"syntology":null},{"url":"/paper/value-understanding-dialect-disparity-in-nlu","slug":"value-understanding-dialect-disparity-in-nlu","title":"VALUE: Understanding Dialect Disparity in NLU","date":"2022-04-06","arxiv_id":"2204.03031","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/value-understanding-dialect-disparity-in-nlu#ran","syntology_url":"https://syntology.ai/paper/2204.03031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03031"}},"official":{"repos":["salt-nlp/value"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/monolingual-and-cross-lingual-acceptability","slug":"monolingual-and-cross-lingual-acceptability","title":"Monolingual and Cross-Lingual Acceptability Judgments with the Italian CoLA corpus","date":"2021-09-24","arxiv_id":"2109.12053","repositories_listed":1,"syntology":null},{"url":"/paper/new-students-on-sesame-street-what-order","slug":"new-students-on-sesame-street-what-order","title":"General Cross-Architecture Distillation of Pretrained Language Models into Matrix Embeddings","date":"2021-09-17","arxiv_id":"2109.08449","repositories_listed":1,"syntology":null},{"url":"/paper/language-models-use-monotonicity-to-assess","slug":"language-models-use-monotonicity-to-assess","title":"Language Models Use Monotonicity to Assess NPI Licensing","date":"2021-05-28","arxiv_id":"2105.13818","repositories_listed":1,"syntology":null},{"url":"/paper/domain-adversarial-fine-tuning-as-an","slug":"domain-adversarial-fine-tuning-as-an","title":"Domain Adversarial Fine-Tuning as an Effective Regularizer","date":"2020-09-28","arxiv_id":"2009.13366","repositories_listed":1,"syntology":null},{"url":"/paper/towards-debiasing-sentence-representations-1","slug":"towards-debiasing-sentence-representations-1","title":"Towards Debiasing Sentence Representations","date":"2020-07-16","arxiv_id":"2007.08100","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-debiasing-sentence-representations-1#ran","syntology_url":"https://syntology.ai/paper/2007.08100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.08100"}},"official":{"repos":["pliang279/sent_debias"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-robustness-of-language-encoders","slug":"on-the-robustness-of-language-encoders","title":"On the Robustness of Language Encoders against Grammatical Errors","date":"2020-05-12","arxiv_id":"2005.05683","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-the-robustness-of-language-encoders#ran","syntology_url":"https://syntology.ai/paper/2005.05683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05683"}},"official":{"repos":["uclanlp/ProbeGrammarRobustness"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/synthesizer-rethinking-self-attention-in","slug":"synthesizer-rethinking-self-attention-in","title":"Synthesizer: Rethinking Self-Attention in Transformer Models","date":"2020-05-02","arxiv_id":"2005.00743","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/synthesizer-rethinking-self-attention-in#ran","syntology_url":"https://syntology.ai/paper/2005.00743","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00743"}},"official":null}},{"url":"/paper/learning-to-encode-position-for-transformer","slug":"learning-to-encode-position-for-transformer","title":"Learning to Encode Position for Transformer with Continuous Dynamical Model","date":"2020-03-13","arxiv_id":"2003.09229","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":2,"n_ran_checked":0,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/learning-to-encode-position-for-transformer#ran","syntology_url":"https://syntology.ai/paper/2003.09229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.09229"}},"official":null}},{"url":"/paper/natural-language-generation-for-effective","slug":"natural-language-generation-for-effective","title":"Natural Language Generation for Effective Knowledge Distillation","date":"2019-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"dissecting-bias-in-llms-a-mechanistic","title":"Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective","date":"2025-06-05","arxiv_id":"2506.05166","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-asr-error-correction-with-conservative","title":"Robust ASR Error Correction with Conservative Data Filtering","date":"2024-07-18","arxiv_id":"2407.13300","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-phonotactics-from-linguistic","title":"Learning Phonotactics from Linguistic Informants","date":"2024-05-08","arxiv_id":"2405.04726","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-free-distillation-of-language-model-by","title":"Data-Free Distillation of Language Model by Text-to-Text Transfer","date":"2023-11-03","arxiv_id":"2311.01689","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-well-can-machine-generated-texts-be","title":"How well can machine-generated texts be identified and can language models be trained to avoid identification?","date":"2023-10-25","arxiv_id":"2310.16992","repositories_listed":0,"syntology":null},{"url":null,"slug":"defense-of-adversarial-ranking-attack-in-text","title":"Defense of Adversarial Ranking Attack in Text Retrieval: Benchmark and Baseline via Detection","date":"2023-07-31","arxiv_id":"2307.16816","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-neural-symbolic-approach-towards","title":"A Neural-Symbolic Approach Towards Identifying Grammatically Correct Sentences","date":"2023-07-16","arxiv_id":"2307.08036","repositories_listed":0,"syntology":null},{"url":null,"slug":"bag-of-tricks-for-effective-language-model","title":"Bag of Tricks for Effective Language Model Pretraining and Downstream Adaptation: A Case Study on GLUE","date":"2023-02-18","arxiv_id":"2302.09268","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-architecture-distillation-using","title":"Cross-Architecture Distillation Using Bidirectional CMOW Embeddings","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-the-uniform-information-density","title":"Revisiting the Uniform Information Density Hypothesis","date":"2021-09-23","arxiv_id":"2109.11635","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-automated-knowledge-mining-and-document","title":"An Automated Knowledge Mining and Document Classification System with Multi-model Transfer Learning","date":"2021-06-24","arxiv_id":"2106.12744","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-integrated-gradients-to-explain","title":"Using Integrated Gradients and Constituency Parse Trees to explain Linguistic Acceptability learnt by BERT","date":"2021-06-01","arxiv_id":"2106.07349","repositories_listed":0,"syntology":null},{"url":null,"slug":"dalaj-a-dataset-for-linguistic-acceptability","title":"DaLAJ - a dataset for linguistic acceptability judgments for Swedish: Format, baseline, sharing","date":"2021-05-14","arxiv_id":"2105.06681","repositories_listed":0,"syntology":null},{"url":"/paper/dalaj-a-dataset-for-linguistic-acceptability-1","slug":"dalaj-a-dataset-for-linguistic-acceptability-1","title":"DaLAJ – a dataset for linguistic acceptability judgments for Swedish","date":"2021-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/clear-contrastive-learning-for-sentence","slug":"clear-contrastive-learning-for-sentence","title":"CLEAR: Contrastive Learning for Sentence Representation","date":"2020-12-31","arxiv_id":"2012.15466","repositories_listed":0,"syntology":null},{"url":null,"slug":"grammaticality-and-language-modelling","title":"Grammaticality and Language Modelling","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"what-would-elsa-do-freezing-layers-during","title":"What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning","date":"2019-11-08","arxiv_id":"1911.03090","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":null,"slug":"grammatical-analysis-of-pretrained-sentence","title":"Linguistic Analysis of Pretrained Sentence Encoders with Acceptability Judgments","date":"2019-01-11","arxiv_id":"1901.03438","repositories_listed":0,"syntology":null},{"url":null,"slug":"grammatical-analysis-of-pretrained-sentence-1","title":"Grammatical Analysis of Pretrained Sentence Encoders with Acceptability Judgments","date":"2018-12-11","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rating-distributions-and-bayesian-inference","title":"Rating Distributions and Bayesian Inference: Enhancing Cognitive Models of Spatial Language Use","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":31,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_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'","n_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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":29,"papers_where_code_ran_first_page":"/task/linguistic-acceptability/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/linguistic-acceptability/papers/ran/1","json":"/task/linguistic-acceptability/papers/ran/1.json","rows":29}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"6f65d43af01dd14a57f385fbbc70817b8c49cd8a2110a8cd399d3ff85fcee1c8","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}