{"task":"Math Word Problem Solving","dataset":"Math23K","metric_names":["Accuracy (5-fold)","Accuracy (training-test)","weakly-supervised"],"rows":[{"id":25191,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"GPT-4 (Teaching-Inspired)","metrics":{"Accuracy (5-fold)":"94.3"},"paper_url":"https://arxiv.org/abs/2410.08068v1","paper_title":"Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models","paper_date":"2024-10-10","code_links":[{"title":"sallytan13/teaching-inspired-prompting","url":"https://github.com/sallytan13/teaching-inspired-prompting"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25192,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"Multi-view* (ours)","metrics":{"Accuracy (5-fold)":"85.2","Accuracy (training-test)":"87.1"},"paper_url":"https://arxiv.org/abs/2210.11694v2","paper_title":"Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem","paper_date":"2022-10-21","code_links":[{"title":"zwq2018/multi-view-consistency-for-mwp","url":"https://github.com/zwq2018/multi-view-consistency-for-mwp"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25193,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"Generate and Rank","metrics":{"Accuracy (5-fold)":"84.3","Accuracy (training-test)":"85.4"},"paper_url":"https://arxiv.org/abs/2109.03034v1","paper_title":"Generate & Rank: A Multi-task Framework for Math Word Problems","paper_date":"2021-09-07","code_links":[],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25194,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"Exp-Tree","metrics":{"Accuracy (5-fold)":"84.1","Accuracy (training-test)":"86.2"},"paper_url":"https://arxiv.org/abs/2310.09619v3","paper_title":"An Expression Tree Decoding Strategy for Mathematical Equation Generation","paper_date":"2023-10-14","code_links":[{"title":"zwq2018/multi-view-consistency-for-mwp","url":"https://github.com/zwq2018/multi-view-consistency-for-mwp"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25195,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"REAL2: Memory-augmented Solver","metrics":{"Accuracy (5-fold)":"83.18","Accuracy (training-test)":"85.2"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25196,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"Roberta-DeductReasoner","metrics":{"Accuracy (5-fold)":"83"},"paper_url":"https://arxiv.org/abs/2203.10316v4","paper_title":"Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction","paper_date":"2022-03-19","code_links":[{"title":"allanj/deductive-mwp","url":"https://github.com/allanj/deductive-mwp"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25197,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"MWP-BERT","metrics":{"Accuracy (5-fold)":"82.4","Accuracy (training-test)":"84.7"},"paper_url":"https://arxiv.org/abs/2107.13435v2","paper_title":"MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving","paper_date":"2021-07-28","code_links":[{"title":"lzhenwen/mwp-bert","url":"https://github.com/lzhenwen/mwp-bert"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25198,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"Recall and Learn","metrics":{"Accuracy (5-fold)":"80.8","Accuracy (training-test)":"82.3"},"paper_url":"https://arxiv.org/abs/2109.13112v1","paper_title":"Recall and Learn: A Memory-augmented Solver for Math Word Problems","paper_date":"2021-09-27","code_links":[{"title":"sfeng-m/real4mwp","url":"https://github.com/sfeng-m/real4mwp"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25199,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"RoBERTaGen","metrics":{"Accuracy (5-fold)":"76.6"},"paper_url":"https://arxiv.org/abs/2109.00799v2","paper_title":"MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers","paper_date":"2021-09-02","code_links":[{"title":"lyh-yf/mwptoolkit","url":"https://github.com/lyh-yf/mwptoolkit"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25200,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"GTS w/ Data Augmentation","metrics":{"Accuracy (5-fold)":"75.9"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25201,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"Graph2Tree","metrics":{"Accuracy (5-fold)":"75.5","Accuracy (training-test)":"77.4"},"paper_url":"https://aclanthology.org/2020.acl-main.362","paper_title":"Graph-to-Tree Learning for Solving Math Word Problems","paper_date":"2020-07-01","code_links":[{"title":"2003pro/Graph2Tree","url":"https://github.com/2003pro/Graph2Tree"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25202,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"SAU-Solver","metrics":{"Accuracy (5-fold)":"74.84"},"paper_url":"https://arxiv.org/abs/2010.06823v1","paper_title":"Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems","paper_date":"2020-10-14","code_links":[{"title":"QinJinghui/SAU-Solver","url":"https://github.com/QinJinghui/SAU-Solver"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25203,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"GTS","metrics":{"Accuracy (5-fold)":"74.3"},"paper_url":"https://www.ijcai.org/Proceedings/2019/736","paper_title":"A Goal-Driven Tree-Structured Neural Model for Math Word Problems","paper_date":"2019-08-10","code_links":[{"title":"ShichaoSun/math_seq2tree","url":"https://github.com/ShichaoSun/math_seq2tree"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25204,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"GROUP-ATT","metrics":{"Accuracy (5-fold)":"66.9","Accuracy (training-test)":"69.5"},"paper_url":"https://aclanthology.org/P19-1619","paper_title":"Modeling Intra-Relation in Math Word Problems with Different Functional Multi-Head Attentions","paper_date":"2019-07-01","code_links":[{"title":"lijierui/group-attention","url":"https://github.com/lijierui/group-attention"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25205,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"Hybrid model w/ SNI","metrics":{"Accuracy (5-fold)":"64.7"},"paper_url":"https://aclanthology.org/D17-1088","paper_title":"Deep Neural Solver for Math Word Problems","paper_date":"2017-09-01","code_links":[],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25206,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"ATHENA (roberta-large)","metrics":{"Accuracy (training-test)":"86.5"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25207,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"ATHENA (roberta-base)","metrics":{"Accuracy (training-test)":"84.4"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25208,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"T-RNN","metrics":{"Accuracy (training-test)":"66.9"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25209,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"LBF","metrics":{"weakly-supervised":"59.8"},"paper_url":"https://arxiv.org/abs/2012.10582v2","paper_title":"Learning by Fixing: Solving Math Word Problems with Weak Supervision","paper_date":"2020-12-19","code_links":[{"title":"evelinehong/LBF","url":"https://github.com/evelinehong/LBF"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94769,"task":"Math Word Problem Solving","parent_task":null,"dataset":"Math23K","model_name":"GPT-4 (Teaching-Inspired)","metrics":{"Accuracy (5-fold)":"94.3"},"paper_url":"https://arxiv.org/abs/2410.08068v1","paper_title":"Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models","paper_date":"2024-10-10","code_links":[{"title":"sallytan13/teaching-inspired-prompting","url":"https://github.com/sallytan13/teaching-inspired-prompting"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94770,"task":"Math Word Problem Solving","parent_task":null,"dataset":"Math23K","model_name":"Multi-view* (ours)","metrics":{"Accuracy (5-fold)":"85.2","Accuracy (training-test)":"87.1"},"paper_url":"https://arxiv.org/abs/2210.11694v2","paper_title":"Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem","paper_date":"2022-10-21","code_links":[{"title":"zwq2018/multi-view-consistency-for-mwp","url":"https://github.com/zwq2018/multi-view-consistency-for-mwp"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94771,"task":"Math Word Problem Solving","parent_task":null,"dataset":"Math23K","model_name":"Generate and Rank","metrics":{"Accuracy (5-fold)":"84.3","Accuracy (training-test)":"85.4"},"paper_url":"https://arxiv.org/abs/2109.03034v1","paper_title":"Generate & Rank: A Multi-task Framework for Math Word Problems","paper_date":"2021-09-07","code_links":[],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94772,"task":"Math Word Problem Solving","parent_task":null,"dataset":"Math23K","model_name":"Exp-Tree","metrics":{"Accuracy (5-fold)":"84.1","Accuracy (training-test)":"86.2"},"paper_url":"https://arxiv.org/abs/2310.09619v3","paper_title":"An Expression Tree Decoding Strategy for Mathematical Equation Generation","paper_date":"2023-10-14","code_links":[{"title":"zwq2018/multi-view-consistency-for-mwp","url":"https://github.com/zwq2018/multi-view-consistency-for-mwp"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94773,"task":"Math Word Problem Solving","parent_task":null,"dataset":"Math23K","model_name":"REAL2: Memory-augmented Solver","metrics":{"Accuracy (5-fold)":"83.18","Accuracy (training-test)":"85.2"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94774,"task":"Math Word Problem Solving","parent_task":null,"dataset":"Math23K","model_name":"Roberta-DeductReasoner","metrics":{"Accuracy (5-fold)":"83"},"paper_url":"https://arxiv.org/abs/2203.10316v4","paper_title":"Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction","paper_date":"2022-03-19","code_links":[{"title":"allanj/deductive-mwp","url":"https://github.com/allanj/deductive-mwp"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94775,"task":"Math Word Problem Solving","parent_task":null,"dataset":"Math23K","model_name":"MWP-BERT","metrics":{"Accuracy (5-fold)":"82.4","Accuracy (training-test)":"84.7"},"paper_url":"https://arxiv.org/abs/2107.13435v2","paper_title":"MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving","paper_date":"2021-07-28","code_links":[{"title":"lzhenwen/mwp-bert","url":"https://github.com/lzhenwen/mwp-bert"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94776,"task":"Math Word Problem Solving","parent_task":null,"dataset":"Math23K","model_name":"Recall and Learn","metrics":{"Accuracy (5-fold)":"80.8","Accuracy (training-test)":"82.3"},"paper_url":"https://arxiv.org/abs/2109.13112v1","paper_title":"Recall and Learn: A Memory-augmented Solver for Math Word Problems","paper_date":"2021-09-27","code_links":[{"title":"sfeng-m/real4mwp","url":"https://github.com/sfeng-m/real4mwp"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94777,"task":"Math Word Problem Solving","parent_task":null,"dataset":"Math23K","model_name":"RoBERTaGen","metrics":{"Accuracy (5-fold)":"76.6"},"paper_url":"https://arxiv.org/abs/2109.00799v2","paper_title":"MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers","paper_date":"2021-09-02","code_links":[{"title":"lyh-yf/mwptoolkit","url":"https://github.com/lyh-yf/mwptoolkit"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94778,"task":"Math Word Problem Solving","parent_task":null,"dataset":"Math23K","model_name":"GTS w/ Data Augmentation","metrics":{"Accuracy (5-fold)":"75.9"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94779,"task":"Math Word Problem Solving","parent_task":null,"dataset":"Math23K","model_name":"Graph2Tree","metrics":{"Accuracy (5-fold)":"75.5","Accuracy (training-test)":"77.4"},"paper_url":"https://aclanthology.org/2020.acl-main.362","paper_title":"Graph-to-Tree Learning for Solving Math Word Problems","paper_date":"2020-07-01","code_links":[{"title":"2003pro/Graph2Tree","url":"https://github.com/2003pro/Graph2Tree"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94780,"task":"Math Word Problem Solving","parent_task":null,"dataset":"Math23K","model_name":"SAU-Solver","metrics":{"Accuracy (5-fold)":"74.84"},"paper_url":"https://arxiv.org/abs/2010.06823v1","paper_title":"Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems","paper_date":"2020-10-14","code_links":[{"title":"QinJinghui/SAU-Solver","url":"https://github.com/QinJinghui/SAU-Solver"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94781,"task":"Math Word Problem Solving","parent_task":null,"dataset":"Math23K","model_name":"GTS","metrics":{"Accuracy (5-fold)":"74.3"},"paper_url":"https://www.ijcai.org/Proceedings/2019/736","paper_title":"A Goal-Driven Tree-Structured Neural Model for Math Word Problems","paper_date":"2019-08-10","code_links":[{"title":"ShichaoSun/math_seq2tree","url":"https://github.com/ShichaoSun/math_seq2tree"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94782,"task":"Math Word Problem Solving","parent_task":null,"dataset":"Math23K","model_name":"GROUP-ATT","metrics":{"Accuracy (5-fold)":"66.9","Accuracy (training-test)":"69.5"},"paper_url":"https://aclanthology.org/P19-1619","paper_title":"Modeling Intra-Relation in Math Word Problems with Different Functional Multi-Head Attentions","paper_date":"2019-07-01","code_links":[{"title":"lijierui/group-attention","url":"https://github.com/lijierui/group-attention"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94783,"task":"Math Word Problem Solving","parent_task":null,"dataset":"Math23K","model_name":"Hybrid model w/ SNI","metrics":{"Accuracy (5-fold)":"64.7"},"paper_url":"https://aclanthology.org/D17-1088","paper_title":"Deep Neural Solver for Math Word Problems","paper_date":"2017-09-01","code_links":[],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94784,"task":"Math Word Problem Solving","parent_task":null,"dataset":"Math23K","model_name":"ATHENA (roberta-large)","metrics":{"Accuracy (training-test)":"86.5"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94785,"task":"Math Word Problem Solving","parent_task":null,"dataset":"Math23K","model_name":"ATHENA (roberta-base)","metrics":{"Accuracy (training-test)":"84.4"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94786,"task":"Math Word Problem Solving","parent_task":null,"dataset":"Math23K","model_name":"T-RNN","metrics":{"Accuracy (training-test)":"66.9"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94787,"task":"Math Word Problem Solving","parent_task":null,"dataset":"Math23K","model_name":"LBF","metrics":{"weakly-supervised":"59.8"},"paper_url":"https://arxiv.org/abs/2012.10582v2","paper_title":"Learning by Fixing: Solving Math Word Problems with Weak Supervision","paper_date":"2020-12-19","code_links":[{"title":"evelinehong/LBF","url":"https://github.com/evelinehong/LBF"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112015,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"GPT-4 (Teaching-Inspired)","metrics":{"Accuracy (5-fold)":"94.3"},"paper_url":"https://arxiv.org/abs/2410.08068v1","paper_title":"Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models","paper_date":"2024-10-10","code_links":[{"title":"sallytan13/teaching-inspired-prompting","url":"https://github.com/sallytan13/teaching-inspired-prompting"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112016,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"Multi-view* (ours)","metrics":{"Accuracy (5-fold)":"85.2","Accuracy (training-test)":"87.1"},"paper_url":"https://arxiv.org/abs/2210.11694v2","paper_title":"Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem","paper_date":"2022-10-21","code_links":[{"title":"zwq2018/multi-view-consistency-for-mwp","url":"https://github.com/zwq2018/multi-view-consistency-for-mwp"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112017,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"Generate and Rank","metrics":{"Accuracy (5-fold)":"84.3","Accuracy (training-test)":"85.4"},"paper_url":"https://arxiv.org/abs/2109.03034v1","paper_title":"Generate & Rank: A Multi-task Framework for Math Word Problems","paper_date":"2021-09-07","code_links":[],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112018,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"Exp-Tree","metrics":{"Accuracy (5-fold)":"84.1","Accuracy (training-test)":"86.2"},"paper_url":"https://arxiv.org/abs/2310.09619v3","paper_title":"An Expression Tree Decoding Strategy for Mathematical Equation Generation","paper_date":"2023-10-14","code_links":[{"title":"zwq2018/multi-view-consistency-for-mwp","url":"https://github.com/zwq2018/multi-view-consistency-for-mwp"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112019,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"REAL2: Memory-augmented Solver","metrics":{"Accuracy (5-fold)":"83.18","Accuracy (training-test)":"85.2"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112020,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"Roberta-DeductReasoner","metrics":{"Accuracy (5-fold)":"83"},"paper_url":"https://arxiv.org/abs/2203.10316v4","paper_title":"Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction","paper_date":"2022-03-19","code_links":[{"title":"allanj/deductive-mwp","url":"https://github.com/allanj/deductive-mwp"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112021,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"MWP-BERT","metrics":{"Accuracy (5-fold)":"82.4","Accuracy (training-test)":"84.7"},"paper_url":"https://arxiv.org/abs/2107.13435v2","paper_title":"MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving","paper_date":"2021-07-28","code_links":[{"title":"lzhenwen/mwp-bert","url":"https://github.com/lzhenwen/mwp-bert"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112022,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"Recall and Learn","metrics":{"Accuracy (5-fold)":"80.8","Accuracy (training-test)":"82.3"},"paper_url":"https://arxiv.org/abs/2109.13112v1","paper_title":"Recall and Learn: A Memory-augmented Solver for Math Word Problems","paper_date":"2021-09-27","code_links":[{"title":"sfeng-m/real4mwp","url":"https://github.com/sfeng-m/real4mwp"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112023,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"RoBERTaGen","metrics":{"Accuracy (5-fold)":"76.6"},"paper_url":"https://arxiv.org/abs/2109.00799v2","paper_title":"MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers","paper_date":"2021-09-02","code_links":[{"title":"lyh-yf/mwptoolkit","url":"https://github.com/lyh-yf/mwptoolkit"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112024,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"GTS w/ Data Augmentation","metrics":{"Accuracy (5-fold)":"75.9"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112025,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"Graph2Tree","metrics":{"Accuracy (5-fold)":"75.5","Accuracy (training-test)":"77.4"},"paper_url":"https://aclanthology.org/2020.acl-main.362","paper_title":"Graph-to-Tree Learning for Solving Math Word Problems","paper_date":"2020-07-01","code_links":[{"title":"2003pro/Graph2Tree","url":"https://github.com/2003pro/Graph2Tree"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112026,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"SAU-Solver","metrics":{"Accuracy (5-fold)":"74.84"},"paper_url":"https://arxiv.org/abs/2010.06823v1","paper_title":"Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems","paper_date":"2020-10-14","code_links":[{"title":"QinJinghui/SAU-Solver","url":"https://github.com/QinJinghui/SAU-Solver"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112027,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"GTS","metrics":{"Accuracy (5-fold)":"74.3"},"paper_url":"https://www.ijcai.org/Proceedings/2019/736","paper_title":"A Goal-Driven Tree-Structured Neural Model for Math Word Problems","paper_date":"2019-08-10","code_links":[{"title":"ShichaoSun/math_seq2tree","url":"https://github.com/ShichaoSun/math_seq2tree"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112028,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"GROUP-ATT","metrics":{"Accuracy (5-fold)":"66.9","Accuracy (training-test)":"69.5"},"paper_url":"https://aclanthology.org/P19-1619","paper_title":"Modeling Intra-Relation in Math Word Problems with Different Functional Multi-Head Attentions","paper_date":"2019-07-01","code_links":[{"title":"lijierui/group-attention","url":"https://github.com/lijierui/group-attention"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112029,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"Hybrid model w/ SNI","metrics":{"Accuracy (5-fold)":"64.7"},"paper_url":"https://aclanthology.org/D17-1088","paper_title":"Deep Neural Solver for Math Word Problems","paper_date":"2017-09-01","code_links":[],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112030,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"ATHENA (roberta-large)","metrics":{"Accuracy (training-test)":"86.5"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112031,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"ATHENA (roberta-base)","metrics":{"Accuracy (training-test)":"84.4"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112032,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"T-RNN","metrics":{"Accuracy (training-test)":"66.9"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112033,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"Math23K","model_name":"LBF","metrics":{"weakly-supervised":"59.8"},"paper_url":"https://arxiv.org/abs/2012.10582v2","paper_title":"Learning by Fixing: Solving Math Word Problems with Weak Supervision","paper_date":"2020-12-19","code_links":[{"title":"evelinehong/LBF","url":"https://github.com/evelinehong/LBF"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120364,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"Math23K","model_name":"GPT-4 (Teaching-Inspired)","metrics":{"Accuracy (5-fold)":"94.3"},"paper_url":"https://arxiv.org/abs/2410.08068v1","paper_title":"Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models","paper_date":"2024-10-10","code_links":[{"title":"sallytan13/teaching-inspired-prompting","url":"https://github.com/sallytan13/teaching-inspired-prompting"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120365,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"Math23K","model_name":"Multi-view* (ours)","metrics":{"Accuracy (5-fold)":"85.2","Accuracy (training-test)":"87.1"},"paper_url":"https://arxiv.org/abs/2210.11694v2","paper_title":"Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem","paper_date":"2022-10-21","code_links":[{"title":"zwq2018/multi-view-consistency-for-mwp","url":"https://github.com/zwq2018/multi-view-consistency-for-mwp"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120366,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"Math23K","model_name":"Generate and Rank","metrics":{"Accuracy (5-fold)":"84.3","Accuracy (training-test)":"85.4"},"paper_url":"https://arxiv.org/abs/2109.03034v1","paper_title":"Generate & Rank: A Multi-task Framework for Math Word Problems","paper_date":"2021-09-07","code_links":[],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120367,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"Math23K","model_name":"Exp-Tree","metrics":{"Accuracy (5-fold)":"84.1","Accuracy (training-test)":"86.2"},"paper_url":"https://arxiv.org/abs/2310.09619v3","paper_title":"An Expression Tree Decoding Strategy for Mathematical Equation Generation","paper_date":"2023-10-14","code_links":[{"title":"zwq2018/multi-view-consistency-for-mwp","url":"https://github.com/zwq2018/multi-view-consistency-for-mwp"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120368,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"Math23K","model_name":"REAL2: Memory-augmented Solver","metrics":{"Accuracy (5-fold)":"83.18","Accuracy (training-test)":"85.2"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120369,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"Math23K","model_name":"Roberta-DeductReasoner","metrics":{"Accuracy (5-fold)":"83"},"paper_url":"https://arxiv.org/abs/2203.10316v4","paper_title":"Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction","paper_date":"2022-03-19","code_links":[{"title":"allanj/deductive-mwp","url":"https://github.com/allanj/deductive-mwp"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120370,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"Math23K","model_name":"MWP-BERT","metrics":{"Accuracy (5-fold)":"82.4","Accuracy (training-test)":"84.7"},"paper_url":"https://arxiv.org/abs/2107.13435v2","paper_title":"MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving","paper_date":"2021-07-28","code_links":[{"title":"lzhenwen/mwp-bert","url":"https://github.com/lzhenwen/mwp-bert"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120371,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"Math23K","model_name":"Recall and Learn","metrics":{"Accuracy (5-fold)":"80.8","Accuracy (training-test)":"82.3"},"paper_url":"https://arxiv.org/abs/2109.13112v1","paper_title":"Recall and Learn: A Memory-augmented Solver for Math Word Problems","paper_date":"2021-09-27","code_links":[{"title":"sfeng-m/real4mwp","url":"https://github.com/sfeng-m/real4mwp"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120372,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"Math23K","model_name":"RoBERTaGen","metrics":{"Accuracy (5-fold)":"76.6"},"paper_url":"https://arxiv.org/abs/2109.00799v2","paper_title":"MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers","paper_date":"2021-09-02","code_links":[{"title":"lyh-yf/mwptoolkit","url":"https://github.com/lyh-yf/mwptoolkit"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120373,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"Math23K","model_name":"GTS w/ Data Augmentation","metrics":{"Accuracy (5-fold)":"75.9"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120374,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"Math23K","model_name":"Graph2Tree","metrics":{"Accuracy (5-fold)":"75.5","Accuracy (training-test)":"77.4"},"paper_url":"https://aclanthology.org/2020.acl-main.362","paper_title":"Graph-to-Tree Learning for Solving Math Word Problems","paper_date":"2020-07-01","code_links":[{"title":"2003pro/Graph2Tree","url":"https://github.com/2003pro/Graph2Tree"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120375,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"Math23K","model_name":"SAU-Solver","metrics":{"Accuracy (5-fold)":"74.84"},"paper_url":"https://arxiv.org/abs/2010.06823v1","paper_title":"Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems","paper_date":"2020-10-14","code_links":[{"title":"QinJinghui/SAU-Solver","url":"https://github.com/QinJinghui/SAU-Solver"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120376,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"Math23K","model_name":"GTS","metrics":{"Accuracy (5-fold)":"74.3"},"paper_url":"https://www.ijcai.org/Proceedings/2019/736","paper_title":"A Goal-Driven Tree-Structured Neural Model for Math Word Problems","paper_date":"2019-08-10","code_links":[{"title":"ShichaoSun/math_seq2tree","url":"https://github.com/ShichaoSun/math_seq2tree"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120377,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"Math23K","model_name":"GROUP-ATT","metrics":{"Accuracy (5-fold)":"66.9","Accuracy (training-test)":"69.5"},"paper_url":"https://aclanthology.org/P19-1619","paper_title":"Modeling Intra-Relation in Math Word Problems with Different Functional Multi-Head Attentions","paper_date":"2019-07-01","code_links":[{"title":"lijierui/group-attention","url":"https://github.com/lijierui/group-attention"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120378,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"Math23K","model_name":"Hybrid model w/ SNI","metrics":{"Accuracy (5-fold)":"64.7"},"paper_url":"https://aclanthology.org/D17-1088","paper_title":"Deep Neural Solver for Math Word Problems","paper_date":"2017-09-01","code_links":[],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120379,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"Math23K","model_name":"ATHENA (roberta-large)","metrics":{"Accuracy (training-test)":"86.5"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120380,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"Math23K","model_name":"ATHENA (roberta-base)","metrics":{"Accuracy (training-test)":"84.4"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120381,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"Math23K","model_name":"T-RNN","metrics":{"Accuracy (training-test)":"66.9"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120382,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"Math23K","model_name":"LBF","metrics":{"weakly-supervised":"59.8"},"paper_url":"https://arxiv.org/abs/2012.10582v2","paper_title":"Learning by Fixing: Solving Math Word Problems with Weak Supervision","paper_date":"2020-12-19","code_links":[{"title":"evelinehong/LBF","url":"https://github.com/evelinehong/LBF"}],"metrics_order":"[\"Accuracy (5-fold)\", \"Accuracy (training-test)\", \"weakly-supervised\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]}]}