{"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/natural-language-understanding","name":"Natural Language Understanding","slug":"natural-language-understanding","description_markdown":"**Natural Language Understanding** is an important field of Natural Language Processing which contains various tasks such as text classification, natural language inference and story comprehension. Applications enabled by natural language understanding range from question answering  to automated reasoning.\r\n\r\n\r\n\r\nSource: [Find a Reasonable Ending for Stories: Does Logic Relation Help the Story Cloze Test?](https://arxiv.org/abs/1812.05411)","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":1978,"papers_with_code":809,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"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":72,"subtasks":2,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/natural-language-understanding-on-pdp60","slug":"natural-language-understanding-on-pdp60","dataset":"PDP60","dataset_url":null,"rows_in_archive":13,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"HNN","paper_title":"A Hybrid Neural Network Model for Commonsense Reasoning","paper_url":"/paper/a-hybrid-neural-network-model-for-commonsense","paper_date":"2019-07-27","arxiv_id":"1907.11983","code_links":[{"title":"namisan/mt-dnn","url":"https://github.com/namisan/mt-dnn"},{"title":"microsoft/MT-DNN","url":"https://github.com/microsoft/MT-DNN"},{"title":"chunhuililili/mt_dnn","url":"https://github.com/chunhuililili/mt_dnn"}],"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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/a-hybrid-neural-network-model-for-commonsense#ran","syntology_url":"https://syntology.ai/paper/1907.11983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11983"}},"official":{"repos":["namisan/mt-dnn"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}}},{"leaderboard":"/sota/natural-language-understanding-on-streusle","slug":"natural-language-understanding-on-streusle","dataset":"STREUSLE","dataset_url":"/dataset/steusle","rows_in_archive":11,"metrics":["Tags (Full) Acc","Role F1 (Preps)","Function F1 (Preps)","Full F1 (Preps)"],"first_row_in_archive_order":{"model":"BERT (pred POS/lemmas)","paper_title":"Lexical Semantic Recognition","paper_url":"/paper/lexical-semantic-recognition","paper_date":"2020-04-30","arxiv_id":"2004.15008","code_links":[{"title":"nert-nlp/streusle","url":"https://github.com/nert-nlp/streusle"},{"title":"nelson-liu/lexical-semantic-recognition","url":"https://github.com/nelson-liu/lexical-semantic-recognition"}],"syntology":null}},{"leaderboard":"/sota/natural-language-understanding-on-lexglue","slug":"natural-language-understanding-on-lexglue","dataset":"LexGLUE","dataset_url":"/dataset/lexglue","rows_in_archive":8,"metrics":["ECtHR Task A","ECtHR Task B","SCOTUS","EUR-LEX","LEDGAR","UNFAIR-ToS","CaseHOLD"],"first_row_in_archive_order":{"model":"BERT","paper_title":"LexGLUE: A Benchmark Dataset for Legal Language Understanding in English","paper_url":"/paper/lexglue-a-benchmark-dataset-for-legal","paper_date":"2021-10-03","arxiv_id":"2110.00976","code_links":[{"title":"coastalcph/lex-glue","url":"https://github.com/coastalcph/lex-glue"}],"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/lexglue-a-benchmark-dataset-for-legal#ran","syntology_url":"https://syntology.ai/paper/2110.00976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.00976"}},"official":{"repos":["coastalcph/lex-glue"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}}},{"leaderboard":"/sota/natural-language-understanding-on-dialoglue-1","slug":"natural-language-understanding-on-dialoglue-1","dataset":"DialoGLUE fewshot","dataset_url":"/dataset/dialoglue","rows_in_archive":5,"metrics":["Average","Banking77 (Acc)","CLINC150 (Acc)","HWU64 (Acc)","Restaurant8k (F-1)","DSTC8 (F-1)","TOP (EM)","MultiWOZ (Joint Goal Acc)"],"first_row_in_archive_order":{"model":"ConvBERT-DG","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/natural-language-understanding-on-dialoglue","slug":"natural-language-understanding-on-dialoglue","dataset":"DialoGLUE full","dataset_url":"/dataset/dialoglue","rows_in_archive":3,"metrics":["Average","Banking77 (Acc)","CLINC150 (Acc)","HWU64 (Acc)","Restaurant8k (F-1)","DSTC8 (F-1)","TOP (EM)","MultiWOZ (Joint Goal Acc)"],"first_row_in_archive_order":{"model":"ConvBERT + Pre + Multi","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/natural-language-understanding-on-glue","slug":"natural-language-understanding-on-glue","dataset":"GLUE","dataset_url":"/dataset/glue","rows_in_archive":2,"metrics":["Average"],"first_row_in_archive_order":{"model":"MT-DNN-SMART","paper_title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","paper_url":"/paper/smart-robust-and-efficient-fine-tuning-for","paper_date":"2019-11-08","arxiv_id":"1911.03437","code_links":[{"title":"namisan/mt-dnn","url":"https://github.com/namisan/mt-dnn"},{"title":"microsoft/MT-DNN","url":"https://github.com/microsoft/MT-DNN"},{"title":"archinetai/smart-pytorch","url":"https://github.com/archinetai/smart-pytorch"},{"title":"archinetai/vat-pytorch","url":"https://github.com/archinetai/vat-pytorch"},{"title":"cliang1453/camero","url":"https://github.com/cliang1453/camero"},{"title":"chunhuililili/mt_dnn","url":"https://github.com/chunhuililili/mt_dnn"}],"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"]}}}}],"datasets":[{"url":"/dataset/glue","name":"GLUE","full_name":"General Language Understanding Evaluation benchmark","num_papers_in_archive":3197},{"url":"/dataset/mmlu","name":"MML","full_name":"Massive Multitask Language Understanding","num_papers_in_archive":1922},{"url":"/dataset/winogrande","name":"WinoGrande","full_name":"","num_papers_in_archive":703},{"url":"/dataset/sgd","name":"SGD","full_name":"Schema-Guided Dialogue","num_papers_in_archive":186},{"url":"/dataset/logiqa","name":"LogiQA","full_name":"","num_papers_in_archive":127},{"url":"/dataset/writingprompts","name":"WritingPrompts","full_name":"","num_papers_in_archive":118},{"url":"/dataset/cosmosqa","name":"CosmosQA","full_name":"","num_papers_in_archive":102},{"url":"/dataset/clue","name":"CLUE","full_name":"Chinese Language Understanding Evaluation Benchmark","num_papers_in_archive":99},{"url":"/dataset/belebele","name":"Belebele","full_name":"","num_papers_in_archive":68},{"url":"/dataset/aqua-rat","name":"AQUA-RAT","full_name":"Algebra Question Answering with Rationales","num_papers_in_archive":64},{"url":"/dataset/lexglue","name":"LexGLUE","full_name":"","num_papers_in_archive":46},{"url":"/dataset/climate-fever","name":"CLIMATE-FEVER","full_name":"","num_papers_in_archive":38},{"url":"/dataset/emobank","name":"EmoBank","full_name":"","num_papers_in_archive":32},{"url":"/dataset/decanlp","name":"decaNLP","full_name":"Natural Language Decathlon Benchmark","num_papers_in_archive":28},{"url":"/dataset/wikicoref","name":"WikiCoref","full_name":"","num_papers_in_archive":28},{"url":"/dataset/crosswoz","name":"CrossWOZ","full_name":"CrossWOZ","num_papers_in_archive":25},{"url":"/dataset/mcscript","name":"MCScript","full_name":"MCScript","num_papers_in_archive":24},{"url":"/dataset/moral-stories","name":"Moral Stories","full_name":"","num_papers_in_archive":24},{"url":"/dataset/recipeqa","name":"RecipeQA","full_name":"","num_papers_in_archive":24},{"url":"/dataset/xglue","name":"XGLUE","full_name":"","num_papers_in_archive":22},{"url":"/dataset/steusle","name":"STREUSLE","full_name":"","num_papers_in_archive":21},{"url":"/dataset/preco","name":"PreCo","full_name":"","num_papers_in_archive":20},{"url":"/dataset/kornli","name":"KorNLI","full_name":null,"num_papers_in_archive":18},{"url":"/dataset/dialoglue","name":"DialoGLUE","full_name":"","num_papers_in_archive":17},{"url":"/dataset/indonlu-benchmark","name":"IndoNLU Benchmark","full_name":"","num_papers_in_archive":14},{"url":"/dataset/fewglue","name":"FewGlue","full_name":"","num_papers_in_archive":13},{"url":"/dataset/jec-qa","name":"JEC-QA","full_name":"","num_papers_in_archive":13},{"url":"/dataset/klej","name":"KLEJ","full_name":"","num_papers_in_archive":13},{"url":"/dataset/korsts","name":"KorSTS","full_name":"","num_papers_in_archive":13},{"url":"/dataset/sara","name":"SARA","full_name":"StAtutory Reasoning Assessment","num_papers_in_archive":13},{"url":"/dataset/epie","name":"EPIE","full_name":"","num_papers_in_archive":12},{"url":"/dataset/perspectrum","name":"Perspectrum","full_name":"","num_papers_in_archive":11},{"url":"/dataset/only-connect-wall-ocw-dataset","name":"OCW","full_name":"Only Connect Wall Dataset and creative problem solving tasks","num_papers_in_archive":10},{"url":"/dataset/mmcu","name":"MMCU","full_name":"Measuring Massive Multitask Chinese Understanding","num_papers_in_archive":9},{"url":"/dataset/orangesum","name":"OrangeSum","full_name":"","num_papers_in_archive":8},{"url":"/dataset/definite-pronoun-resolution-dataset","name":"Definite Pronoun Resolution Dataset","full_name":"","num_papers_in_archive":7},{"url":"/dataset/medal","name":"MeDAL","full_name":"","num_papers_in_archive":7},{"url":"/dataset/imppres","name":"IMPPRES","full_name":"","num_papers_in_archive":6},{"url":"/dataset/nlu","name":"NLU++","full_name":"NLLU++ : A Multi-Label, Slot-Rich, Generalisable Dataset for Natural Language Understanding in Task-Oriented Dialogue","num_papers_in_archive":6},{"url":"/dataset/vispro","name":"VisPro","full_name":"VisPro","num_papers_in_archive":6},{"url":"/dataset/wikicrem","name":"WikiCREM","full_name":"WikiCREM","num_papers_in_archive":6},{"url":"/dataset/sp-10k","name":"SP-10K","full_name":"","num_papers_in_archive":5},{"url":"/dataset/xwino","name":"XWINO","full_name":"","num_papers_in_archive":4},{"url":"/dataset/allegro-reviews","name":"Allegro Reviews","full_name":"","num_papers_in_archive":3},{"url":"/dataset/arabic-dataset-for-commonsense-validation","name":"Arabic Dataset for Commonsense Validation¬†","full_name":"","num_papers_in_archive":3},{"url":"/dataset/chq-summ","name":"CHQ-Summ","full_name":"Consumer Healthcare Question Summarization","num_papers_in_archive":3},{"url":"/dataset/emotional-dialogue-acts","name":"Emotional Dialogue Acts","full_name":"","num_papers_in_archive":3},{"url":"/dataset/eth-py150-open","name":"ETH Py150 Open","full_name":"","num_papers_in_archive":3},{"url":"/dataset/geoglue","name":"GeoGLUE","full_name":"GeoGraphic Language Understanding Evaluation Benchmark","num_papers_in_archive":3},{"url":"/dataset/justice","name":"JUSTICE","full_name":"JUSTICE: A Dataset for Supreme Court’s Judgment Prediction","num_papers_in_archive":3},{"url":"/dataset/muld","name":"MuLD","full_name":"Multitask Long Document Benchmark","num_papers_in_archive":3},{"url":"/dataset/nusacrowd","name":"NusaCrowd","full_name":"","num_papers_in_archive":3},{"url":"/dataset/wikitext-tl-39","name":"WikiText-TL-39","full_name":"","num_papers_in_archive":3},{"url":"/dataset/rumedbench","name":"RuMedBench","full_name":"","num_papers_in_archive":2},{"url":"/dataset/bigscience-p3","name":"bigscience/P3","full_name":"bigscience/P3, split='ai2_arc_ARC_Challenge_pick_the_most_correct_option'","num_papers_in_archive":1},{"url":"/dataset/candor-corpus-1","name":"CANDOR Corpus","full_name":"CANDOR = Conversation: A Naturalistic Dataset of Online Recordings","num_papers_in_archive":1},{"url":"/dataset/chatlog","name":"ChatLog","full_name":"","num_papers_in_archive":1},{"url":"/dataset/clues","name":"CLUES","full_name":"Constrained Language Understanding Evaluation Standard","num_papers_in_archive":1},{"url":"/dataset/dialog-based-language-learning-dataset","name":"Dialog-based Language Learning dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/discoeval","name":"DiscoEval","full_name":"Discourse Evaluation","num_papers_in_archive":1},{"url":"/dataset/epic30m","name":"EPIC30M","full_name":"","num_papers_in_archive":1},{"url":"/dataset/expunations","name":"ExPUNations","full_name":"","num_papers_in_archive":1},{"url":"/dataset/fewglue-64-labeled","name":"FewGLUE_64_labeled","full_name":"A new version of FewGLUE with 64 training examples","num_papers_in_archive":1},{"url":"/dataset/idk-mrc","name":"IDK-MRC","full_name":"","num_papers_in_archive":1},{"url":"/dataset/imagifilter","name":"ImagiFilter","full_name":"","num_papers_in_archive":1},{"url":"/dataset/maven-arg","name":"MAVEN-Arg","full_name":"MAVEN-Arguments","num_papers_in_archive":1},{"url":"/dataset/multiwoz-coref","name":"MultiWOZ-coref","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/nlu-evaluation-corpora","name":"NLU Evaluation Corpora","full_name":"","num_papers_in_archive":1},{"url":"/dataset/phrase-in-context","name":"Phrase-in-Context","full_name":"Phrase-in-Context","num_papers_in_archive":1},{"url":"/dataset/pre-trained-transliterated-embeddings-for","name":"Pre-trained Transliterated Embeddings for Indian Languages","full_name":"","num_papers_in_archive":1},{"url":"/dataset/thunder-nubench","name":"Thunder-NUBench","full_name":"","num_papers_in_archive":1},{"url":"/dataset/indirectrequests","name":"IndirectRequests","full_name":"IndirectRequests","num_papers_in_archive":0}],"subtasks":[{"url":"/task/emotional-dialogue-acts","name":"Emotional Dialogue Acts"},{"url":"/task/vietnamese-social-media-text-processing","name":"Vietnamese Social Media Text Processing"}],"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":20,"rows_per_page":100,"shown":100,"of":1978,"of_with_code":809,"tagged_in_all":1978,"counts":{"archive_papers_tagged":1978,"with_a_code_link":809,"where_syntology_ran_a_sample":185,"not_listed_spam_title":0,"listed":1978,"listed_where_code_ran":185,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":152,"every_run_a_failure_of_syntologys_instrument":33,"listed_with_a_run_with_no_instrument_failure":152,"listed_every_run_a_failure_of_syntologys_instrument":33,"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/attention-is-all-you-need","slug":"attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","arxiv_id":"1706.03762","repositories_listed":595,"syntology":{"n":946,"n_ran":610,"n_constructed":293,"n_ran_checked":529,"n_instrument":81,"n_unverified":336,"n_honours":45,"n_violates":15,"n_no_contract":469,"n_pointer_only":451,"phrase":"610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified","sample_list":"/paper/attention-is-all-you-need#ran","syntology_url":"https://syntology.ai/paper/1706.03762","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.03762"}},"official":{"repos":["tensorflow/tensor2tensor"],"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/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/learning-transferable-visual-models-from","slug":"learning-transferable-visual-models-from","title":"Learning Transferable Visual Models From Natural Language Supervision","date":"2021-02-26","arxiv_id":"2103.00020","repositories_listed":82,"syntology":{"n":20,"n_ran":16,"n_constructed":0,"n_ran_checked":2,"n_instrument":14,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":16,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 14 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/learning-transferable-visual-models-from#ran","syntology_url":"https://syntology.ai/paper/2103.00020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00020"}},"official":{"repos":["openai/CLIP"],"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/electra-pre-training-text-encoders-as-1","slug":"electra-pre-training-text-encoders-as-1","title":"ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators","date":"2020-03-23","arxiv_id":"2003.10555","repositories_listed":19,"syntology":{"n":40,"n_ran":31,"n_constructed":7,"n_ran_checked":18,"n_instrument":13,"n_unverified":9,"n_honours":2,"n_violates":2,"n_no_contract":14,"n_pointer_only":10,"phrase":"31 ran (of which 7 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 2 violated, 14 with no contract checked; 13 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/electra-pre-training-text-encoders-as-1#ran","syntology_url":"https://syntology.ai/paper/2003.10555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.10555"}},"official":{"repos":["google-research/electra"],"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/a-neural-conversational-model","slug":"a-neural-conversational-model","title":"A Neural Conversational Model","date":"2015-06-19","arxiv_id":"1506.05869","repositories_listed":18,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-neural-conversational-model#ran","syntology_url":"https://syntology.ai/paper/1506.05869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1506.05869"}},"official":null}},{"url":"/paper/cross-lingual-language-model-pretraining","slug":"cross-lingual-language-model-pretraining","title":"Cross-lingual Language Model Pretraining","date":"2019-01-22","arxiv_id":"1901.07291","repositories_listed":17,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cross-lingual-language-model-pretraining#ran","syntology_url":"https://syntology.ai/paper/1901.07291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.07291"}},"official":null}},{"url":"/paper/bert-for-joint-intent-classification-and-slot","slug":"bert-for-joint-intent-classification-and-slot","title":"BERT for Joint Intent Classification and Slot Filling","date":"2019-02-28","arxiv_id":"1902.10909","repositories_listed":16,"syntology":{"n":32,"n_ran":26,"n_constructed":0,"n_ran_checked":18,"n_instrument":8,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":17,"n_pointer_only":5,"phrase":"26 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 1 honoured, 0 violated, 17 with no contract checked; 8 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/bert-for-joint-intent-classification-and-slot#ran","syntology_url":"https://syntology.ai/paper/1902.10909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.10909"}},"official":null}},{"url":"/paper/snips-voice-platform-an-embedded-spoken","slug":"snips-voice-platform-an-embedded-spoken","title":"Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces","date":"2018-05-25","arxiv_id":"1805.10190","repositories_listed":16,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/snips-voice-platform-an-embedded-spoken#ran","syntology_url":"https://syntology.ai/paper/1805.10190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.10190"}},"official":{"repos":["snipsco/nlu-benchmark","snipsco/snips-nlu"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"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/improving-language-understanding-by","slug":"improving-language-understanding-by","title":"Improving Language Understanding by Generative Pre-Training","date":"2018-06-11","arxiv_id":null,"repositories_listed":13,"syntology":null},{"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/neural-architecture-search-with-reinforcement","slug":"neural-architecture-search-with-reinforcement","title":"Neural Architecture Search with Reinforcement Learning","date":"2016-11-05","arxiv_id":"1611.01578","repositories_listed":12,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/neural-architecture-search-with-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1611.01578","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01578"}},"official":{"repos":["tensorflow/models"],"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/know-what-you-dont-know-unanswerable","slug":"know-what-you-dont-know-unanswerable","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","date":"2018-06-11","arxiv_id":"1806.03822","repositories_listed":11,"syntology":null},{"url":"/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","repositories_listed":11,"syntology":{"n":14,"n_ran":14,"n_constructed":0,"n_ran_checked":12,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":10,"n_pointer_only":1,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 1 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","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"}},"official":null}},{"url":"/paper/gpt-understands-too","slug":"gpt-understands-too","title":"GPT Understands, Too","date":"2021-03-18","arxiv_id":"2103.10385","repositories_listed":10,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-understands-too#ran","syntology_url":"https://syntology.ai/paper/2103.10385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.10385"}},"official":{"repos":["THUDM/P-tuning"],"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/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/nezha-neural-contextualized-representation","slug":"nezha-neural-contextualized-representation","title":"NEZHA: Neural Contextualized Representation for Chinese Language Understanding","date":"2019-08-31","arxiv_id":"1909.00204","repositories_listed":10,"syntology":null},{"url":"/paper/colbert-efficient-and-effective-passage","slug":"colbert-efficient-and-effective-passage","title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","date":"2020-04-27","arxiv_id":"2004.12832","repositories_listed":9,"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/colbert-efficient-and-effective-passage#ran","syntology_url":"https://syntology.ai/paper/2004.12832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.12832"}},"official":{"repos":["stanford-futuredata/ColBERT"],"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/unified-language-model-pre-training-for","slug":"unified-language-model-pre-training-for","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","date":"2019-05-08","arxiv_id":"1905.03197","repositories_listed":9,"syntology":null},{"url":"/paper/benchmarking-natural-language-understanding","slug":"benchmarking-natural-language-understanding","title":"Benchmarking Natural Language Understanding Services for building Conversational Agents","date":"2019-03-13","arxiv_id":"1903.05566","repositories_listed":9,"syntology":null},{"url":"/paper/all-nlp-tasks-are-generation-tasks-a-general","slug":"all-nlp-tasks-are-generation-tasks-a-general","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","date":"2021-03-18","arxiv_id":"2103.10360","repositories_listed":8,"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/all-nlp-tasks-are-generation-tasks-a-general#ran","syntology_url":"https://syntology.ai/paper/2103.10360","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.10360"}},"official":{"repos":["THUDM/GLM"],"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/convbert-improving-bert-with-span-based","slug":"convbert-improving-bert-with-span-based","title":"ConvBERT: Improving BERT with Span-based Dynamic Convolution","date":"2020-08-06","arxiv_id":"2008.02496","repositories_listed":8,"syntology":null},{"url":"/paper/i-bert-integer-only-bert-quantization","slug":"i-bert-integer-only-bert-quantization","title":"I-BERT: Integer-only BERT Quantization","date":"2021-01-05","arxiv_id":"2101.01321","repositories_listed":7,"syntology":null},{"url":"/paper/leveraging-pre-trained-checkpoints-for","slug":"leveraging-pre-trained-checkpoints-for","title":"Leveraging Pre-trained Checkpoints for Sequence Generation Tasks","date":"2019-07-29","arxiv_id":"1907.12461","repositories_listed":7,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/leveraging-pre-trained-checkpoints-for#ran","syntology_url":"https://syntology.ai/paper/1907.12461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.12461"}},"official":null}},{"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/massive-a-1m-example-multilingual-natural","slug":"massive-a-1m-example-multilingual-natural","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","date":"2022-04-18","arxiv_id":"2204.08582","repositories_listed":6,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/massive-a-1m-example-multilingual-natural#ran","syntology_url":"https://syntology.ai/paper/2204.08582","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08582"}},"official":{"repos":["alexa/massive"],"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/a-relational-tsetlin-machine-with","slug":"a-relational-tsetlin-machine-with","title":"A Relational Tsetlin Machine with Applications to Natural Language Understanding","date":"2021-02-22","arxiv_id":"2102.10952","repositories_listed":6,"syntology":null},{"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/efficient-self-supervised-learning-with","slug":"efficient-self-supervised-learning-with","title":"Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language","date":"2022-12-14","arxiv_id":"2212.07525","repositories_listed":5,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/efficient-self-supervised-learning-with#ran","syntology_url":"https://syntology.ai/paper/2212.07525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.07525"}},"official":{"repos":["facebookresearch/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/pangu-a-large-scale-autoregressive-pretrained","slug":"pangu-a-large-scale-autoregressive-pretrained","title":"PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation","date":"2021-04-26","arxiv_id":"2104.12369","repositories_listed":5,"syntology":null},{"url":"/paper/barthez-a-skilled-pretrained-french-sequence","slug":"barthez-a-skilled-pretrained-french-sequence","title":"BARThez: a Skilled Pretrained French Sequence-to-Sequence Model","date":"2020-10-23","arxiv_id":"2010.12321","repositories_listed":5,"syntology":null},{"url":"/paper/it-s-not-just-size-that-matters-small","slug":"it-s-not-just-size-that-matters-small","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","date":"2020-09-15","arxiv_id":"2009.07118","repositories_listed":5,"syntology":null},{"url":"/paper/clutrr-a-diagnostic-benchmark-for-inductive","slug":"clutrr-a-diagnostic-benchmark-for-inductive","title":"CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text","date":"2019-08-16","arxiv_id":"1908.06177","repositories_listed":5,"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/clutrr-a-diagnostic-benchmark-for-inductive#ran","syntology_url":"https://syntology.ai/paper/1908.06177","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.06177"}},"official":{"repos":["facebookresearch/clutrr"],"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/a-comprehensive-survey-on-graph-neural","slug":"a-comprehensive-survey-on-graph-neural","title":"A Comprehensive Survey on Graph Neural Networks","date":"2019-01-03","arxiv_id":"1901.00596","repositories_listed":5,"syntology":null},{"url":"/paper/lamp-when-large-language-models-meet","slug":"lamp-when-large-language-models-meet","title":"LaMP: When Large Language Models Meet Personalization","date":"2023-04-22","arxiv_id":"2304.11406","repositories_listed":4,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lamp-when-large-language-models-meet#ran","syntology_url":"https://syntology.ai/paper/2304.11406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.11406"}},"official":null}},{"url":"/paper/klue-korean-language-understanding-evaluation","slug":"klue-korean-language-understanding-evaluation","title":"KLUE: Korean Language Understanding Evaluation","date":"2021-05-20","arxiv_id":"2105.09680","repositories_listed":4,"syntology":null},{"url":"/paper/rethinking-embedding-coupling-in-pre-trained-1","slug":"rethinking-embedding-coupling-in-pre-trained-1","title":"Rethinking embedding coupling in pre-trained language models","date":"2020-10-24","arxiv_id":"2010.12821","repositories_listed":4,"syntology":null},{"url":"/paper/collaborative-multi-agent-dialogue-model","slug":"collaborative-multi-agent-dialogue-model","title":"Collaborative Multi-Agent Dialogue Model Training Via Reinforcement Learning","date":"2019-07-11","arxiv_id":"1907.05507","repositories_listed":4,"syntology":null},{"url":"/paper/mind-the-gap-a-balanced-corpus-of-gendered","slug":"mind-the-gap-a-balanced-corpus-of-gendered","title":"Mind the GAP: A Balanced Corpus of Gendered Ambiguous Pronouns","date":"2018-10-11","arxiv_id":"1810.05201","repositories_listed":4,"syntology":null},{"url":"/paper/bone-block-affine-transformation-as-parameter","slug":"bone-block-affine-transformation-as-parameter","title":"Balancing LoRA Performance and Efficiency with Simple Shard Sharing","date":"2024-09-19","arxiv_id":"2409.15371","repositories_listed":3,"syntology":null},{"url":"/paper/mathodyssey-benchmarking-mathematical-problem","slug":"mathodyssey-benchmarking-mathematical-problem","title":"MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models Using Odyssey Math Data","date":"2024-06-26","arxiv_id":"2406.18321","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mathodyssey-benchmarking-mathematical-problem#ran","syntology_url":"https://syntology.ai/paper/2406.18321","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18321"}},"official":null}},{"url":"/paper/medcare-advancing-medical-llms-through","slug":"medcare-advancing-medical-llms-through","title":"MedCare: Advancing Medical LLMs through Decoupling Clinical Alignment and Knowledge Aggregation","date":"2024-06-25","arxiv_id":"2406.17484","repositories_listed":3,"syntology":null},{"url":"/paper/encoder-vs-decoder-comparative-analysis-of","slug":"encoder-vs-decoder-comparative-analysis-of","title":"Encoder vs Decoder: Comparative Analysis of Encoder and Decoder Language Models on Multilingual NLU Tasks","date":"2024-06-19","arxiv_id":"2406.13469","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/encoder-vs-decoder-comparative-analysis-of#ran","syntology_url":"https://syntology.ai/paper/2406.13469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13469"}},"official":null}},{"url":"/paper/datacomp-lm-in-search-of-the-next-generation","slug":"datacomp-lm-in-search-of-the-next-generation","title":"DataComp-LM: In search of the next generation of training sets for language models","date":"2024-06-17","arxiv_id":"2406.11794","repositories_listed":3,"syntology":{"n":22,"n_ran":22,"n_constructed":0,"n_ran_checked":9,"n_instrument":13,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 13 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/datacomp-lm-in-search-of-the-next-generation#ran","syntology_url":"https://syntology.ai/paper/2406.11794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11794"}},"official":null}},{"url":"/paper/mixture-of-agents-enhances-large-language","slug":"mixture-of-agents-enhances-large-language","title":"Mixture-of-Agents Enhances Large Language Model Capabilities","date":"2024-06-07","arxiv_id":"2406.04692","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mixture-of-agents-enhances-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.04692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04692"}},"official":null}},{"url":"/paper/cephalo-multi-modal-vision-language-models","slug":"cephalo-multi-modal-vision-language-models","title":"Cephalo: Multi-Modal Vision-Language Models for Bio-Inspired Materials Analysis and Design","date":"2024-05-29","arxiv_id":"2405.19076","repositories_listed":3,"syntology":null},{"url":"/paper/efficient-large-language-models-a-survey","slug":"efficient-large-language-models-a-survey","title":"Efficient Large Language Models: A Survey","date":"2023-12-06","arxiv_id":"2312.03863","repositories_listed":3,"syntology":null},{"url":"/paper/2309-06085","slug":"2309-06085","title":"BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models","date":"2023-09-12","arxiv_id":"2309.06085","repositories_listed":3,"syntology":null},{"url":"/paper/scaling-transformer-to-1m-tokens-and-beyond","slug":"scaling-transformer-to-1m-tokens-and-beyond","title":"Scaling Transformer to 1M tokens and beyond with RMT","date":"2023-04-19","arxiv_id":"2304.11062","repositories_listed":3,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/scaling-transformer-to-1m-tokens-and-beyond#ran","syntology_url":"https://syntology.ai/paper/2304.11062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.11062"}},"official":{"repos":["booydar/t5-experiments"],"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/decoder-tuning-efficient-language","slug":"decoder-tuning-efficient-language","title":"Decoder Tuning: Efficient Language Understanding as Decoding","date":"2022-12-16","arxiv_id":"2212.08408","repositories_listed":3,"syntology":null},{"url":"/paper/atco2-corpus-a-large-scale-dataset-for","slug":"atco2-corpus-a-large-scale-dataset-for","title":"ATCO2 corpus: A Large-Scale Dataset for Research on Automatic Speech Recognition and Natural Language Understanding of Air Traffic Control Communications","date":"2022-11-08","arxiv_id":"2211.04054","repositories_listed":3,"syntology":null},{"url":"/paper/debertav3-improving-deberta-using-electra","slug":"debertav3-improving-deberta-using-electra","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","date":"2021-11-18","arxiv_id":"2111.09543","repositories_listed":3,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/debertav3-improving-deberta-using-electra#ran","syntology_url":"https://syntology.ai/paper/2111.09543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09543"}},"official":{"repos":["microsoft/DeBERTa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/programming-puzzles","slug":"programming-puzzles","title":"Programming Puzzles","date":"2021-06-10","arxiv_id":"2106.05784","repositories_listed":3,"syntology":null},{"url":"/paper/what-makes-good-in-context-examples-for-gpt-3","slug":"what-makes-good-in-context-examples-for-gpt-3","title":"What Makes Good In-Context Examples for GPT-$3$?","date":"2021-01-17","arxiv_id":"2101.06804","repositories_listed":3,"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/what-makes-good-in-context-examples-for-gpt-3#ran","syntology_url":"https://syntology.ai/paper/2101.06804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.06804"}},"official":null}},{"url":"/paper/optimal-subarchitecture-extraction-for-bert","slug":"optimal-subarchitecture-extraction-for-bert","title":"Optimal Subarchitecture Extraction For BERT","date":"2020-10-20","arxiv_id":"2010.10499","repositories_listed":3,"syntology":null},{"url":"/paper/comet-atomic-2020-on-symbolic-and-neural","slug":"comet-atomic-2020-on-symbolic-and-neural","title":"COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs","date":"2020-10-12","arxiv_id":"2010.05953","repositories_listed":3,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/comet-atomic-2020-on-symbolic-and-neural#ran","syntology_url":"https://syntology.ai/paper/2010.05953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.05953"}},"official":{"repos":["allenai/comet-atomic-2020"],"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":["listed","official"]}}},{"url":"/paper/multiwoz-2-3-a-multi-domain-task-oriented","slug":"multiwoz-2-3-a-multi-domain-task-oriented","title":"MultiWOZ 2.3: A multi-domain task-oriented dialogue dataset enhanced with annotation corrections and co-reference annotation","date":"2020-10-12","arxiv_id":"2010.05594","repositories_listed":3,"syntology":null},{"url":"/paper/indonlu-benchmark-and-resources-for","slug":"indonlu-benchmark-and-resources-for","title":"IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding","date":"2020-09-11","arxiv_id":"2009.05387","repositories_listed":3,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/indonlu-benchmark-and-resources-for#ran","syntology_url":"https://syntology.ai/paper/2009.05387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.05387"}},"official":{"repos":["indobenchmark/indonlu"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/autotrans-automating-transformer-design-via","slug":"autotrans-automating-transformer-design-via","title":"AutoTrans: Automating Transformer Design via Reinforced Architecture Search","date":"2020-09-04","arxiv_id":"2009.02070","repositories_listed":3,"syntology":null},{"url":"/paper/is-supervised-syntactic-parsing-beneficial","slug":"is-supervised-syntactic-parsing-beneficial","title":"Is Supervised Syntactic Parsing Beneficial for Language Understanding? An Empirical Investigation","date":"2020-08-15","arxiv_id":"2008.06788","repositories_listed":3,"syntology":null},{"url":"/paper/rethinking-the-positional-encoding-in","slug":"rethinking-the-positional-encoding-in","title":"Rethinking Positional Encoding in Language Pre-training","date":"2020-06-28","arxiv_id":"2006.15595","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rethinking-the-positional-encoding-in#ran","syntology_url":"https://syntology.ai/paper/2006.15595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.15595"}},"official":{"repos":["guolinke/TUPE"],"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":["listed","official"]}}},{"url":"/paper/end-to-end-slot-alignment-and-recognition-for","slug":"end-to-end-slot-alignment-and-recognition-for","title":"End-to-End Slot Alignment and Recognition for Cross-Lingual NLU","date":"2020-04-29","arxiv_id":"2004.14353","repositories_listed":3,"syntology":null},{"url":"/paper/probabilistically-masked-language-model","slug":"probabilistically-masked-language-model","title":"Probabilistically Masked Language Model Capable of Autoregressive Generation in Arbitrary Word Order","date":"2020-04-24","arxiv_id":"2004.11579","repositories_listed":3,"syntology":{"n":35,"n_ran":21,"n_constructed":1,"n_ran_checked":12,"n_instrument":9,"n_unverified":14,"n_honours":4,"n_violates":3,"n_no_contract":5,"n_pointer_only":29,"phrase":"21 ran (of which 1 constructed an object rather than computing a result; 12 with no instrument failure: 4 honoured, 3 violated, 5 with no contract checked; 9 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/probabilistically-masked-language-model#ran","syntology_url":"https://syntology.ai/paper/2004.11579","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.11579"}},"official":{"repos":["huawei-noah/Pretrained-Language-Model"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":1,"n_ran_no_instrument_failure":8,"n_unverified":13,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/adversarial-training-for-large-neural","slug":"adversarial-training-for-large-neural","title":"Adversarial Training for Large Neural Language Models","date":"2020-04-20","arxiv_id":"2004.08994","repositories_listed":3,"syntology":null},{"url":"/paper/clue-a-chinese-language-understanding","slug":"clue-a-chinese-language-understanding","title":"CLUE: A Chinese Language Understanding Evaluation Benchmark","date":"2020-04-13","arxiv_id":"2004.05986","repositories_listed":3,"syntology":null},{"url":"/paper/kornli-and-korsts-new-benchmark-datasets-for","slug":"kornli-and-korsts-new-benchmark-datasets-for","title":"KorNLI and KorSTS: New Benchmark Datasets for Korean Natural Language Understanding","date":"2020-04-07","arxiv_id":"2004.03289","repositories_listed":3,"syntology":null},{"url":"/paper/sum-product-networks-a-survey","slug":"sum-product-networks-a-survey","title":"Sum-product networks: A survey","date":"2020-04-02","arxiv_id":"2004.01167","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/sum-product-networks-a-survey#ran","syntology_url":"https://syntology.ai/paper/2004.01167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.01167"}},"official":{"repos":["arranger1044/awesome-spn","SPFlow/SPFlow"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/unilmv2-pseudo-masked-language-models-for","slug":"unilmv2-pseudo-masked-language-models-for","title":"UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training","date":"2020-02-28","arxiv_id":"2002.12804","repositories_listed":3,"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/unilmv2-pseudo-masked-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2002.12804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.12804"}},"official":{"repos":["microsoft/unilm"],"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/the-microsoft-toolkit-of-multi-task-deep","slug":"the-microsoft-toolkit-of-multi-task-deep","title":"The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding","date":"2020-02-19","arxiv_id":"2002.07972","repositories_listed":3,"syntology":null},{"url":"/paper/incorporating-bert-into-neural-machine-1","slug":"incorporating-bert-into-neural-machine-1","title":"Incorporating BERT into Neural Machine Translation","date":"2020-02-17","arxiv_id":"2002.06823","repositories_listed":3,"syntology":null},{"url":"/paper/using-speech-synthesis-to-train-end-to-end","slug":"using-speech-synthesis-to-train-end-to-end","title":"Using Speech Synthesis to Train End-to-End Spoken Language Understanding Models","date":"2019-10-21","arxiv_id":"1910.09463","repositories_listed":3,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/using-speech-synthesis-to-train-end-to-end#ran","syntology_url":"https://syntology.ai/paper/1910.09463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.09463"}},"official":{"repos":["lorenlugosch/end-to-end-SLU"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/ludwig-a-type-based-declarative-deep-learning","slug":"ludwig-a-type-based-declarative-deep-learning","title":"Ludwig: a type-based declarative deep learning toolbox","date":"2019-09-17","arxiv_id":"1909.07930","repositories_listed":3,"syntology":null},{"url":"/paper/a-hybrid-neural-network-model-for-commonsense","slug":"a-hybrid-neural-network-model-for-commonsense","title":"A Hybrid Neural Network Model for Commonsense Reasoning","date":"2019-07-27","arxiv_id":"1907.11983","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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/a-hybrid-neural-network-model-for-commonsense#ran","syntology_url":"https://syntology.ai/paper/1907.11983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11983"}},"official":{"repos":["namisan/mt-dnn"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/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","repositories_listed":3,"syntology":null},{"url":"/paper/joint-slot-filling-and-intent-detection-via","slug":"joint-slot-filling-and-intent-detection-via","title":"Joint Slot Filling and Intent Detection via Capsule Neural Networks","date":"2018-12-22","arxiv_id":"1812.09471","repositories_listed":3,"syntology":null},{"url":"/paper/visual-re-ranking-with-natural-language","slug":"visual-re-ranking-with-natural-language","title":"Visual Re-ranking with Natural Language Understanding for Text Spotting","date":"2018-10-29","arxiv_id":"1810.12738","repositories_listed":3,"syntology":null},{"url":"/paper/dissent-sentence-representation-learning-from","slug":"dissent-sentence-representation-learning-from","title":"DisSent: Sentence Representation Learning from Explicit Discourse Relations","date":"2017-10-12","arxiv_id":"1710.04334","repositories_listed":3,"syntology":null},{"url":"/paper/neural-semantic-encoders","slug":"neural-semantic-encoders","title":"Neural Semantic Encoders","date":"2016-07-14","arxiv_id":"1607.04315","repositories_listed":3,"syntology":null},{"url":"/paper/exact-aggregation-for-federated-and-efficient","slug":"exact-aggregation-for-federated-and-efficient","title":"FedEx-LoRA: Exact Aggregation for Federated and Efficient Fine-Tuning of Foundation Models","date":"2024-10-12","arxiv_id":"2410.09432","repositories_listed":2,"syntology":null},{"url":"/paper/towards-enhancing-linked-data-retrieval-in","slug":"towards-enhancing-linked-data-retrieval-in","title":"Towards Enhancing Linked Data Retrieval in Conversational UIs using Large Language Models","date":"2024-09-24","arxiv_id":"2409.16220","repositories_listed":2,"syntology":null},{"url":"/paper/fine-tuning-large-language-models-with-human","slug":"fine-tuning-large-language-models-with-human","title":"Evaluating Fine-Tuning Efficiency of Human-Inspired Learning Strategies in Medical Question Answering","date":"2024-08-15","arxiv_id":"2408.07888","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":10,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/fine-tuning-large-language-models-with-human#ran","syntology_url":"https://syntology.ai/paper/2408.07888","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.07888"}},"official":{"repos":["Oxford-AI-for-Society/human-learning-strategies"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/gamebench-evaluating-strategic-reasoning","slug":"gamebench-evaluating-strategic-reasoning","title":"GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents","date":"2024-06-07","arxiv_id":"2406.06613","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gamebench-evaluating-strategic-reasoning#ran","syntology_url":"https://syntology.ai/paper/2406.06613","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06613"}},"official":{"repos":["Joshuaclymer/GameBench"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/how-good-are-low-bit-quantized-llama3-models","slug":"how-good-are-low-bit-quantized-llama3-models","title":"An empirical study of LLaMA3 quantization: from LLMs to MLLMs","date":"2024-04-22","arxiv_id":"2404.14047","repositories_listed":2,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/how-good-are-low-bit-quantized-llama3-models#ran","syntology_url":"https://syntology.ai/paper/2404.14047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.14047"}},"official":{"repos":["macaronlin/llama3-quantization"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/tabsqlify-enhancing-reasoning-capabilities-of","slug":"tabsqlify-enhancing-reasoning-capabilities-of","title":"TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition","date":"2024-04-15","arxiv_id":"2404.10150","repositories_listed":2,"syntology":{"n":15,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":8,"n_honours":6,"n_violates":0,"n_no_contract":0,"n_pointer_only":15,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 6 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/tabsqlify-enhancing-reasoning-capabilities-of#ran","syntology_url":"https://syntology.ai/paper/2404.10150","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10150"}},"official":{"repos":["mahadi-nahid/tabsqlify"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/ming-moe-enhancing-medical-multi-task","slug":"ming-moe-enhancing-medical-multi-task","title":"MING-MOE: Enhancing Medical Multi-Task Learning in Large Language Models with Sparse Mixture of Low-Rank Adapter Experts","date":"2024-04-13","arxiv_id":"2404.09027","repositories_listed":2,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/ming-moe-enhancing-medical-multi-task#ran","syntology_url":"https://syntology.ai/paper/2404.09027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09027"}},"official":{"repos":["mediabrain-sjtu/ming"],"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":["listed","official"]}}},{"url":"/paper/on-training-data-influence-of-gpt-models","slug":"on-training-data-influence-of-gpt-models","title":"On Training Data Influence of GPT Models","date":"2024-04-11","arxiv_id":"2404.07840","repositories_listed":2,"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/on-training-data-influence-of-gpt-models#ran","syntology_url":"https://syntology.ai/paper/2404.07840","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07840"}},"official":{"repos":["eleutherai/pythia","ernie-research/gptfluence"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-democratized-flood-risk-management-an","slug":"towards-democratized-flood-risk-management-an","title":"Towards Democratized Flood Risk Management: An Advanced AI Assistant Enabled by GPT-4 for Enhanced Interpretability and Public Engagement","date":"2024-03-05","arxiv_id":"2403.03188","repositories_listed":2,"syntology":null},{"url":"/paper/turna-a-turkish-encoder-decoder-language","slug":"turna-a-turkish-encoder-decoder-language","title":"TURNA: A Turkish Encoder-Decoder Language Model for Enhanced Understanding and Generation","date":"2024-01-25","arxiv_id":"2401.14373","repositories_listed":2,"syntology":null},{"url":"/paper/mario-math-reasoning-with-code-interpreter","slug":"mario-math-reasoning-with-code-interpreter","title":"MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline","date":"2024-01-16","arxiv_id":"2401.08190","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/mario-math-reasoning-with-code-interpreter#ran","syntology_url":"https://syntology.ai/paper/2401.08190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08190"}},"official":{"repos":["mario-math-reasoning/mario"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/automatic-disfluency-detection-from","slug":"automatic-disfluency-detection-from","title":"Automatic Disfluency Detection from Untranscribed Speech","date":"2023-11-01","arxiv_id":"2311.00867","repositories_listed":2,"syntology":null},{"url":"/paper/back-transcription-as-a-method-for-evaluating","slug":"back-transcription-as-a-method-for-evaluating","title":"Back Transcription as a Method for Evaluating Robustness of Natural Language Understanding Models to Speech Recognition Errors","date":"2023-10-25","arxiv_id":"2310.16609","repositories_listed":2,"syntology":null},{"url":"/paper/reflection-tuning-data-recycling-improves-llm","slug":"reflection-tuning-data-recycling-improves-llm","title":"Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning","date":"2023-10-18","arxiv_id":"2310.11716","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":3,"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/reflection-tuning-data-recycling-improves-llm#ran","syntology_url":"https://syntology.ai/paper/2310.11716","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.11716"}},"official":{"repos":["mingliiii/reflection_tuning"],"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/sib-200-a-simple-inclusive-and-big-evaluation","slug":"sib-200-a-simple-inclusive-and-big-evaluation","title":"SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects","date":"2023-09-14","arxiv_id":"2309.07445","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/sib-200-a-simple-inclusive-and-big-evaluation#ran","syntology_url":"https://syntology.ai/paper/2309.07445","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07445"}},"official":{"repos":["dadelani/sib-200"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-belebele-benchmark-a-parallel-reading","slug":"the-belebele-benchmark-a-parallel-reading","title":"The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants","date":"2023-08-31","arxiv_id":"2308.16884","repositories_listed":2,"syntology":{"n":6,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"0 ran · 6 unverified","sample_list":"/paper/the-belebele-benchmark-a-parallel-reading#ran","syntology_url":"https://syntology.ai/paper/2308.16884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.16884"}},"official":{"repos":["facebookresearch/belebele"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":[]}}},{"url":"/paper/bgglue-a-bulgarian-general-language","slug":"bgglue-a-bulgarian-general-language","title":"bgGLUE: A Bulgarian General Language Understanding Evaluation Benchmark","date":"2023-06-04","arxiv_id":"2306.02349","repositories_listed":2,"syntology":null},{"url":"/paper/tess-text-to-text-self-conditioned-simplex","slug":"tess-text-to-text-self-conditioned-simplex","title":"TESS: Text-to-Text Self-Conditioned Simplex Diffusion","date":"2023-05-15","arxiv_id":"2305.08379","repositories_listed":2,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/tess-text-to-text-self-conditioned-simplex#ran","syntology_url":"https://syntology.ai/paper/2305.08379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.08379"}},"official":{"repos":["allenai/tess-diffusion"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/a-comprehensive-analysis-of-adapter","slug":"a-comprehensive-analysis-of-adapter","title":"A Comprehensive Analysis of Adapter Efficiency","date":"2023-05-12","arxiv_id":"2305.07491","repositories_listed":2,"syntology":null},{"url":"/paper/evaluation-of-chatgpt-as-a-question-answering","slug":"evaluation-of-chatgpt-as-a-question-answering","title":"Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family","date":"2023-03-14","arxiv_id":"2303.07992","repositories_listed":2,"syntology":null},{"url":"/paper/a-persian-benchmark-for-joint-intent","slug":"a-persian-benchmark-for-joint-intent","title":"A Persian Benchmark for Joint Intent Detection and Slot Filling","date":"2023-03-01","arxiv_id":"2303.00408","repositories_listed":2,"syntology":null},{"url":"/paper/topic-modelling-of-swedish-newspaper-articles","slug":"topic-modelling-of-swedish-newspaper-articles","title":"Topic Modelling of Swedish Newspaper Articles about Coronavirus: a Case Study using Latent Dirichlet Allocation Method","date":"2023-01-08","arxiv_id":"2301.03029","repositories_listed":2,"syntology":null}],"syntology_records":49,"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":11,"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-understanding-on-glue","since_archive":"/sota/natural-language-understanding-on-glue#since-judged","papers_judged":11,"placed":0}]},"papers_where_code_ran":185,"papers_where_code_ran_first_page":"/task/natural-language-understanding/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":"archive","page":2,"of":20,"url":"/task/natural-language-understanding/papers/2","json":"/task/natural-language-understanding/papers/2.json","rows":100},{"order":"archive","page":3,"of":20,"url":"/task/natural-language-understanding/papers/3","json":"/task/natural-language-understanding/papers/3.json","rows":100},{"order":"archive","page":4,"of":20,"url":"/task/natural-language-understanding/papers/4","json":"/task/natural-language-understanding/papers/4.json","rows":100},{"order":"archive","page":5,"of":20,"url":"/task/natural-language-understanding/papers/5","json":"/task/natural-language-understanding/papers/5.json","rows":100},{"order":"archive","page":6,"of":20,"url":"/task/natural-language-understanding/papers/6","json":"/task/natural-language-understanding/papers/6.json","rows":100},{"order":"archive","page":7,"of":20,"url":"/task/natural-language-understanding/papers/7","json":"/task/natural-language-understanding/papers/7.json","rows":100},{"order":"archive","page":8,"of":20,"url":"/task/natural-language-understanding/papers/8","json":"/task/natural-language-understanding/papers/8.json","rows":100},{"order":"archive","page":9,"of":20,"url":"/task/natural-language-understanding/papers/9","json":"/task/natural-language-understanding/papers/9.json","rows":100},{"order":"archive","page":10,"of":20,"url":"/task/natural-language-understanding/papers/10","json":"/task/natural-language-understanding/papers/10.json","rows":100},{"order":"archive","page":11,"of":20,"url":"/task/natural-language-understanding/papers/11","json":"/task/natural-language-understanding/papers/11.json","rows":100},{"order":"archive","page":12,"of":20,"url":"/task/natural-language-understanding/papers/12","json":"/task/natural-language-understanding/papers/12.json","rows":100},{"order":"archive","page":13,"of":20,"url":"/task/natural-language-understanding/papers/13","json":"/task/natural-language-understanding/papers/13.json","rows":100},{"order":"archive","page":14,"of":20,"url":"/task/natural-language-understanding/papers/14","json":"/task/natural-language-understanding/papers/14.json","rows":100},{"order":"archive","page":15,"of":20,"url":"/task/natural-language-understanding/papers/15","json":"/task/natural-language-understanding/papers/15.json","rows":100},{"order":"archive","page":16,"of":20,"url":"/task/natural-language-understanding/papers/16","json":"/task/natural-language-understanding/papers/16.json","rows":100},{"order":"archive","page":17,"of":20,"url":"/task/natural-language-understanding/papers/17","json":"/task/natural-language-understanding/papers/17.json","rows":100},{"order":"archive","page":18,"of":20,"url":"/task/natural-language-understanding/papers/18","json":"/task/natural-language-understanding/papers/18.json","rows":100},{"order":"archive","page":19,"of":20,"url":"/task/natural-language-understanding/papers/19","json":"/task/natural-language-understanding/papers/19.json","rows":100},{"order":"archive","page":20,"of":20,"url":"/task/natural-language-understanding/papers/20","json":"/task/natural-language-understanding/papers/20.json","rows":78},{"order":"ran","page":1,"of":2,"url":"/task/natural-language-understanding/papers/ran/1","json":"/task/natural-language-understanding/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/natural-language-understanding/papers/ran/2","json":"/task/natural-language-understanding/papers/ran/2.json","rows":85}],"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":"51141deeeecafe6f896bba5859dfeab66fb2f632628b32816f46163efd91dee9","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}