{"task":"Long-range modeling","dataset":"SCROLLS","metric_names":["Avg.","GovRep","SumScr","QMSum","Qspr","Nrtv","QALT EM-T/H","CNLI"],"rows":[{"id":33778,"task":"Long-range modeling","parent_task":"Language Modelling","dataset":"SCROLLS","model_name":"CoLT5 XL","metrics":{"Avg.":"43.51","CNLI":"88.4","GovRep":"61.3/32.2/33.8","Nrtv":"31.1","QALT EM-T/H":"48.1/43.8","QMSum":"36.2/12.9/24.3","Qspr":"53.9","SumScr":"36.4/10.2/21.7"},"paper_url":"https://arxiv.org/abs/2303.09752v3","paper_title":"CoLT5: Faster Long-Range Transformers with Conditional Computation","paper_date":"2023-03-17","code_links":[],"metrics_order":"[\"Avg.\", \"GovRep\", \"SumScr\", \"QMSum\", \"Qspr\", \"Nrtv\", \"QALT EM-T/H\", \"CNLI\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33779,"task":"Long-range modeling","parent_task":"Language Modelling","dataset":"SCROLLS","model_name":"LongT5 XL","metrics":{"Avg.":"42.53","CNLI":"88.2","GovRep":"61.1 / 32.3 / 33.7","Nrtv":"29.3","QALT EM-T/H":"46.0 / 42.1","QMSum":"34.9 / 11.8 / 23.5","Qspr":"53.1","SumScr":"35.8 / 9.6 / 21.1"},"paper_url":"https://arxiv.org/abs/2112.07916v2","paper_title":"LongT5: Efficient Text-To-Text Transformer for Long Sequences","paper_date":"2021-12-15","code_links":[{"title":"google-research/longt5","url":"https://github.com/google-research/longt5"},{"title":"utsjiyaoli/qa-attack","url":"https://github.com/utsjiyaoli/qa-attack"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/longt5"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/longt5"}],"metrics_order":"[\"Avg.\", \"GovRep\", \"SumScr\", \"QMSum\", \"Qspr\", \"Nrtv\", \"QALT EM-T/H\", \"CNLI\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33780,"task":"Long-range modeling","parent_task":"Language Modelling","dataset":"SCROLLS","model_name":"LongT5 Large","metrics":{"Avg.":"41.03","CNLI":"87.3","GovRep":"61.3/32.2/33.8","Nrtv":"27.2","QALT EM-T/H":"40.6 / 38.6","QMSum":"35.1 / 12.0 / 23.3","Qspr":"52.3","SumScr":"60.3 / 31.1 / 32.8"},"paper_url":"https://arxiv.org/abs/2112.07916v2","paper_title":"LongT5: Efficient Text-To-Text Transformer for Long Sequences","paper_date":"2021-12-15","code_links":[{"title":"google-research/longt5","url":"https://github.com/google-research/longt5"},{"title":"utsjiyaoli/qa-attack","url":"https://github.com/utsjiyaoli/qa-attack"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/longt5"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/longt5"}],"metrics_order":"[\"Avg.\", \"GovRep\", \"SumScr\", \"QMSum\", \"Qspr\", \"Nrtv\", \"QALT EM-T/H\", \"CNLI\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33781,"task":"Long-range modeling","parent_task":"Language Modelling","dataset":"SCROLLS","model_name":"BART-LS","metrics":{"Avg.":"39.76","CNLI":"87.1","GovRep":"59.4 / 29.8 / 30.8","Nrtv":"26.2","QALT EM-T/H":"37.8 / 34.0","QMSum":"35.1 / 11.0 / 22.0","Qspr":"48.7","SumScr":"37.7 / 10.2 / 21.5"},"paper_url":"https://arxiv.org/abs/2209.10052v2","paper_title":"Adapting Pretrained Text-to-Text Models for Long Text Sequences","paper_date":"2022-09-21","code_links":[{"title":"facebookresearch/bart_ls","url":"https://github.com/facebookresearch/bart_ls"}],"metrics_order":"[\"Avg.\", \"GovRep\", \"SumScr\", \"QMSum\", \"Qspr\", \"Nrtv\", \"QALT EM-T/H\", \"CNLI\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33782,"task":"Long-range modeling","parent_task":"Language Modelling","dataset":"SCROLLS","model_name":"LongT5 Base","metrics":{"Avg.":"38.6","CNLI":"85.6","GovRep":"57.7 / 30.0 / 31.4","Nrtv":"23.0","QALT EM-T/H":"37.9 / 36.6","QMSum":"33.9 / 11.0 / 22.8","Qspr":"46.6","SumScr":"34.8 / 9.6 / 21.1"},"paper_url":"https://arxiv.org/abs/2112.07916v2","paper_title":"LongT5: Efficient Text-To-Text Transformer for Long Sequences","paper_date":"2021-12-15","code_links":[{"title":"google-research/longt5","url":"https://github.com/google-research/longt5"},{"title":"utsjiyaoli/qa-attack","url":"https://github.com/utsjiyaoli/qa-attack"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/longt5"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/longt5"}],"metrics_order":"[\"Avg.\", \"GovRep\", \"SumScr\", \"QMSum\", \"Qspr\", \"Nrtv\", \"QALT EM-T/H\", \"CNLI\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33783,"task":"Long-range modeling","parent_task":"Language Modelling","dataset":"SCROLLS","model_name":"BART-large SLED","metrics":{"Avg.":"37.99","CNLI":"87.3","GovRep":"57.5 / 26.3 / 27.4","Nrtv":"24.1","QALT EM-T/H":"34.8 / 34.8","QMSum":"34.2 / 11.0 / 22.0","Qspr":"46.9","SumScr":"35.2 / 8.7 / 19.4"},"paper_url":"https://arxiv.org/abs/2208.00748v3","paper_title":"Efficient Long-Text Understanding with Short-Text Models","paper_date":"2022-08-01","code_links":[{"title":"mivg/sled","url":"https://github.com/mivg/sled"}],"metrics_order":"[\"Avg.\", \"GovRep\", \"SumScr\", \"QMSum\", \"Qspr\", \"Nrtv\", \"QALT EM-T/H\", \"CNLI\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33784,"task":"Long-range modeling","parent_task":"Language Modelling","dataset":"SCROLLS","model_name":"UL2","metrics":{"Avg.":"37.87","GovRep":"53.6 / 26.1 / 28.8","Nrtv":"24.2","QALT EM-T/H":"45.8 / 40.7","QMSum":"31.1 / 8.5 / 20.4","Qspr":"37.6","SumScr":"32.9 / 7.8 / 19.4"},"paper_url":"https://arxiv.org/abs/2205.05131v3","paper_title":"UL2: Unifying Language Learning Paradigms","paper_date":"2022-05-10","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research"},{"title":"opennlg/openba-v2","url":"https://github.com/opennlg/openba-v2"}],"metrics_order":"[\"Avg.\", \"GovRep\", \"SumScr\", \"QMSum\", \"Qspr\", \"Nrtv\", \"QALT EM-T/H\", \"CNLI\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33785,"task":"Long-range modeling","parent_task":"Language Modelling","dataset":"SCROLLS","model_name":"LED Base","metrics":{"Avg.":"29.16","CNLI":"71.5","GovRep":"56.2 / 26.6 / 28.8","Nrtv":"18.5","QALT EM-T/H":"25.8 / 25.4\t","QMSum":"25.1 / 6.7 / 18.8","Qspr":"26.6","SumScr":"24.2 / 4.5 / 15.4"},"paper_url":"https://arxiv.org/abs/2201.03533v2","paper_title":"SCROLLS: Standardized CompaRison Over Long Language Sequences","paper_date":"2022-01-10","code_links":[{"title":"tau-nlp/scrolls","url":"https://github.com/tau-nlp/scrolls"},{"title":"mivg/sled","url":"https://github.com/mivg/sled"}],"metrics_order":"[\"Avg.\", \"GovRep\", \"SumScr\", \"QMSum\", \"Qspr\", \"Nrtv\", \"QALT EM-T/H\", \"CNLI\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33786,"task":"Long-range modeling","parent_task":"Language Modelling","dataset":"SCROLLS","model_name":"BART Base","metrics":{"Avg.":"29.01","CNLI":"77.4","GovRep":"47.9 / 18.6 / 22.7","Nrtv":"15.4","QALT EM-T/H":"26.0 / 25.9","QMSum":"30.2 / 8.7 / 20.7","Qspr":"26.3","SumScr":"27.2 / 4.9 / 16.7"},"paper_url":"https://arxiv.org/abs/2201.03533v2","paper_title":"SCROLLS: Standardized CompaRison Over Long Language Sequences","paper_date":"2022-01-10","code_links":[{"title":"tau-nlp/scrolls","url":"https://github.com/tau-nlp/scrolls"},{"title":"mivg/sled","url":"https://github.com/mivg/sled"}],"metrics_order":"[\"Avg.\", \"GovRep\", \"SumScr\", \"QMSum\", \"Qspr\", \"Nrtv\", \"QALT EM-T/H\", \"CNLI\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33787,"task":"Long-range modeling","parent_task":"Language Modelling","dataset":"SCROLLS","model_name":"Naive","metrics":{"Avg.":"19.35","CNLI":"66","GovRep":"45.3 / 17.9 / 20.8","Nrtv":"1.5","QALT EM-T/H":"25.2 / 26.1","QMSum":"14.2 / 2.0 / 9.3","Qspr":"3.4","SumScr":"19.6 / 1.8 / 11.0"},"paper_url":"https://arxiv.org/abs/2201.03533v2","paper_title":"SCROLLS: Standardized CompaRison Over Long Language Sequences","paper_date":"2022-01-10","code_links":[{"title":"tau-nlp/scrolls","url":"https://github.com/tau-nlp/scrolls"},{"title":"mivg/sled","url":"https://github.com/mivg/sled"}],"metrics_order":"[\"Avg.\", \"GovRep\", \"SumScr\", \"QMSum\", \"Qspr\", \"Nrtv\", \"QALT EM-T/H\", \"CNLI\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33788,"task":"Long-range modeling","parent_task":"Language Modelling","dataset":"SCROLLS","model_name":"PEGASUS-X","metrics":{"GovRep":"60.3 / 30.0 / 31.5","QMSum":"33.2 / 9.6 / 21.6 ","SumScr":"35.7 / 9.1 / 20.6"},"paper_url":"https://arxiv.org/abs/2208.04347v1","paper_title":"Investigating Efficiently Extending Transformers for Long Input Summarization","paper_date":"2022-08-08","code_links":[{"title":"google-research/pegasus","url":"https://github.com/google-research/pegasus"},{"title":"MindCode-4/code-2","url":"https://github.com/MindCode-4/code-2/tree/main/pegasus_x"}],"metrics_order":"[\"Avg.\", \"GovRep\", \"SumScr\", \"QMSum\", \"Qspr\", \"Nrtv\", \"QALT EM-T/H\", \"CNLI\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33789,"task":"Long-range modeling","parent_task":"Language Modelling","dataset":"SCROLLS","model_name":"PEGASUS-X-Base","metrics":{"GovRep":"59.3 / 29.3 / 30.9","QMSum":"32.9 / 9.8 / 21.4","SumScr":" 35.0 / 8.9 / 20.4"},"paper_url":"https://arxiv.org/abs/2208.04347v1","paper_title":"Investigating Efficiently Extending Transformers for Long Input Summarization","paper_date":"2022-08-08","code_links":[{"title":"google-research/pegasus","url":"https://github.com/google-research/pegasus"},{"title":"MindCode-4/code-2","url":"https://github.com/MindCode-4/code-2/tree/main/pegasus_x"}],"metrics_order":"[\"Avg.\", \"GovRep\", \"SumScr\", \"QMSum\", \"Qspr\", \"Nrtv\", \"QALT EM-T/H\", \"CNLI\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33790,"task":"Long-range modeling","parent_task":"Language Modelling","dataset":"SCROLLS","model_name":"UL2 20B","metrics":{"CNLI":"88.7"},"paper_url":"https://arxiv.org/abs/2205.05131v3","paper_title":"UL2: Unifying Language Learning Paradigms","paper_date":"2022-05-10","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research"},{"title":"opennlg/openba-v2","url":"https://github.com/opennlg/openba-v2"}],"metrics_order":"[\"Avg.\", \"GovRep\", \"SumScr\", \"QMSum\", \"Qspr\", \"Nrtv\", \"QALT EM-T/H\", \"CNLI\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]}]}