{"task":"Question Answering","dataset":"HotpotQA","metric_names":["JOINT-F1","ANS-EM","ANS-F1","SUP-EM","SUP-F1","JOINT-EM"],"rows":[{"id":23570,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"Beam Retrieval","metrics":{"ANS-EM":"0.727","ANS-F1":"0.850","JOINT-EM":"0.505","JOINT-F1":"0.775","SUP-EM":"0.663","SUP-F1":"0.901"},"paper_url":"https://arxiv.org/abs/2308.08973v2","paper_title":"End-to-End Beam Retrieval for Multi-Hop Question Answering","paper_date":"2023-08-17","code_links":[{"title":"ShayekhBinIslam/openrag","url":"https://github.com/ShayekhBinIslam/openrag"},{"title":"canghongjian/beam_retriever","url":"https://github.com/canghongjian/beam_retriever"},{"title":"Alab-NII/2wikimultihop","url":"https://github.com/Alab-NII/2wikimultihop"}],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23571,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"BigBird-etc","metrics":{"ANS-F1":"0.755","JOINT-F1":"0.736","SUP-F1":"0.891"},"paper_url":"https://arxiv.org/abs/2007.14062v2","paper_title":"Big Bird: Transformers for Longer Sequences","paper_date":"2020-07-28","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/official/nlp/projects/bigbird"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/bigbird"},{"title":"facebookresearch/xformers","url":"https://github.com/facebookresearch/xformers"},{"title":"google-research/bigbird","url":"https://github.com/google-research/bigbird"},{"title":"monologg/kobigbird","url":"https://github.com/monologg/kobigbird"},{"title":"mim-solutions/bert_for_longer_texts","url":"https://github.com/mim-solutions/bert_for_longer_texts"},{"title":"mim-solutions/roberta_for_longer_texts","url":"https://github.com/mim-solutions/roberta_for_longer_texts"},{"title":"sajjjadayobi/ParsBigBird","url":"https://github.com/sajjjadayobi/ParsBigBird"},{"title":"thefonseca/factorsum","url":"https://github.com/thefonseca/factorsum"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/big_bird"},{"title":"sergeykramp/mthesis-bigbird-embeddings","url":"https://github.com/sergeykramp/mthesis-bigbird-embeddings"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/big_bird"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/bigbird_pegasus"}],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23572,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"AISO","metrics":{"ANS-EM":"0.675","ANS-F1":"0.805","JOINT-EM":"0.449","JOINT-F1":"0.720","SUP-EM":"0.612","SUP-F1":"0.860"},"paper_url":"https://arxiv.org/abs/2109.06747v1","paper_title":"Adaptive Information Seeking for Open-Domain Question Answering","paper_date":"2021-09-14","code_links":[{"title":"zycdev/aiso","url":"https://github.com/zycdev/aiso"}],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23573,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"Chain-of-Skills","metrics":{"ANS-EM":"0.674","ANS-F1":"0.801","JOINT-EM":"0.457","JOINT-F1":"0.717","SUP-EM":"0.613","SUP-F1":"0.853"},"paper_url":"https://arxiv.org/abs/2305.03130v2","paper_title":"Chain-of-Skills: A Configurable Model for Open-domain Question Answering","paper_date":"2023-05-04","code_links":[{"title":"mayer123/udt-qa","url":"https://github.com/mayer123/udt-qa"}],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23574,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"TPRR","metrics":{"ANS-EM":"0.670","ANS-F1":"0.795","JOINT-EM":"0.444","JOINT-F1":"0.708","SUP-EM":"0.594","SUP-F1":"0.843"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23575,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"HopRetriever + Sp-search","metrics":{"ANS-EM":"0.671","ANS-F1":"0.799","JOINT-EM":"0.432","JOINT-F1":"0.706","SUP-EM":"0.574","SUP-F1":"0.835"},"paper_url":"https://arxiv.org/abs/2012.15534v1","paper_title":"HopRetriever: Retrieve Hops over Wikipedia to Answer Complex Questions","paper_date":"2020-12-31","code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23576,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"EBS-Large","metrics":{"ANS-EM":"0.662","ANS-F1":"0.793","JOINT-EM":"0.420","JOINT-F1":"0.700","SUP-EM":"0.573","SUP-F1":"0.840"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23577,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"HopRetriever","metrics":{"ANS-EM":"0.671","ANS-F1":"0.799","JOINT-EM":"0.431","JOINT-F1":"0.698","SUP-EM":"0.572","SUP-F1":"0.826"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23578,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"IRRR+","metrics":{"ANS-EM":"0.663","ANS-F1":"0.791","JOINT-EM":"0.428","JOINT-F1":"0.696","SUP-EM":"0.569","SUP-F1":"0.832"},"paper_url":"https://arxiv.org/abs/2010.12527v4","paper_title":"Answering Open-Domain Questions of Varying Reasoning Steps from Text","paper_date":"2020-10-23","code_links":[{"title":"beerqa/irrr","url":"https://github.com/beerqa/irrr"}],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23579,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"EBS-SH","metrics":{"ANS-EM":"0.655","ANS-F1":"0.786","JOINT-EM":"0.409","JOINT-F1":"0.689","SUP-EM":"0.559","SUP-F1":"0.831"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23580,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"IRRR","metrics":{"ANS-EM":"0.657","ANS-F1":"0.782","JOINT-EM":"0.421","JOINT-F1":"0.686","SUP-EM":"0.559","SUP-F1":"0.821"},"paper_url":"https://arxiv.org/abs/2010.12527v4","paper_title":"Answering Open-Domain Questions of Varying Reasoning Steps from Text","paper_date":"2020-10-23","code_links":[{"title":"beerqa/irrr","url":"https://github.com/beerqa/irrr"}],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23581,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"HopRetriever-V2","metrics":{"ANS-EM":"0.648","ANS-F1":"0.778","JOINT-EM":"0.410","JOINT-F1":"0.678","SUP-EM":"0.561","SUP-F1":"0.818"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23582,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"AFSGraph-retriever","metrics":{"ANS-EM":"0.646","ANS-F1":"0.778","JOINT-EM":"0.411","JOINT-F1":"0.670","SUP-EM":"0.557","SUP-F1":"0.812"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23583,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"Recursive Dense Retriever","metrics":{"ANS-EM":"0.623","ANS-F1":"0.753","JOINT-EM":"0.418","JOINT-F1":"0.666","SUP-EM":"0.575","SUP-F1":"0.809"},"paper_url":"https://arxiv.org/abs/2009.12756v2","paper_title":"Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval","paper_date":"2020-09-27","code_links":[{"title":"facebookresearch/multihop_dense_retrieval","url":"https://github.com/facebookresearch/multihop_dense_retrieval"}],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23584,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"Step-by-Step Retriever","metrics":{"ANS-EM":"0.630","ANS-F1":"0.754","JOINT-EM":"0.404","JOINT-F1":"0.662","SUP-EM":"0.546","SUP-F1":"0.800"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23585,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"DDRQA","metrics":{"ANS-EM":"0.625","ANS-F1":"0.759","JOINT-EM":"0.360","JOINT-F1":"0.639","SUP-EM":"0.510","SUP-F1":"0.789"},"paper_url":"https://arxiv.org/abs/2009.07465v5","paper_title":"Answering Any-hop Open-domain Questions with Iterative Document Reranking","paper_date":"2020-09-16","code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23586,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"HopRetriever-V1","metrics":{"ANS-EM":"0.608","ANS-F1":"0.739","JOINT-EM":"0.380","JOINT-F1":"0.639","SUP-EM":"0.531","SUP-F1":"0.793"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23587,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"DR model large","metrics":{"ANS-EM":"0.620","ANS-F1":"0.753","JOINT-EM":"0.354","JOINT-F1":"0.630","SUP-EM":"0.499","SUP-F1":"0.778"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23588,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"Model name","metrics":{"ANS-EM":"0.617","ANS-F1":"0.746","JOINT-EM":"0.368","JOINT-F1":"0.629","SUP-EM":"0.500","SUP-F1":"0.772"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23589,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"HopAns","metrics":{"ANS-EM":"0.617","ANS-F1":"0.746","JOINT-EM":"0.368","JOINT-F1":"0.629","SUP-EM":"0.500","SUP-F1":"0.772"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23590,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"Anonymous","metrics":{"ANS-EM":"0.604","ANS-F1":"0.732","JOINT-EM":"0.380","JOINT-F1":"0.629","SUP-EM":"0.520","SUP-F1":"0.771"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23591,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"Multi-dimensional-AFSGraph","metrics":{"ANS-EM":"0.615","ANS-F1":"0.746","JOINT-EM":"0.362","JOINT-F1":"0.624","SUP-EM":"0.503","SUP-F1":"0.772"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23592,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"HGN-albert + SemanticRetrievalMRS IR","metrics":{"ANS-EM":"0.597","ANS-F1":"0.714","JOINT-EM":"0.379","JOINT-F1":"0.623","SUP-EM":"0.510","SUP-F1":"0.774"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23593,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"Tree-shaped-cluster","metrics":{"ANS-EM":"0.603","ANS-F1":"0.731","JOINT-EM":"0.359","JOINT-F1":"0.617","SUP-EM":"0.499","SUP-F1":"0.768"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23594,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"AFSgraph","metrics":{"ANS-EM":"0.601","ANS-F1":"0.730","JOINT-EM":"0.359","JOINT-F1":"0.617","SUP-EM":"0.500","SUP-F1":"0.769"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23595,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"Robustly Fine-tuned Graph-based Recurrent Retriever","metrics":{"ANS-EM":"0.600","ANS-F1":"0.730","JOINT-EM":"0.354","JOINT-F1":"0.612","SUP-EM":"0.491","SUP-F1":"0.764"},"paper_url":"https://arxiv.org/abs/1911.10470v2","paper_title":"Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering","paper_date":"2019-11-24","code_links":[{"title":"AkariAsai/learning_to_retrieve_reasoning_paths","url":"https://github.com/AkariAsai/learning_to_retrieve_reasoning_paths"},{"title":"AkariAsai/XORQA","url":"https://github.com/AkariAsai/XORQA"}],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23596,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"AFSgraph  model","metrics":{"ANS-EM":"0.601","ANS-F1":"0.730","JOINT-EM":"0.350","JOINT-F1":"0.609","SUP-EM":"0.485","SUP-F1":"0.759"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23597,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"HGN-large + SemanticRetrievalMRS IR","metrics":{"ANS-EM":"0.579","ANS-F1":"0.699","JOINT-EM":"0.372","JOINT-F1":"0.607","SUP-EM":"0.510","SUP-F1":"0.768"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23598,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"RoBERTa-DenseRetriever-Fast","metrics":{"ANS-EM":"0.598","ANS-F1":"0.727","JOINT-EM":"0.345","JOINT-F1":"0.602","SUP-EM":"0.480","SUP-F1":"0.749"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23599,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"DPR-recurrent","metrics":{"ANS-EM":"0.598","ANS-F1":"0.727","JOINT-EM":"0.345","JOINT-F1":"0.602","SUP-EM":"0.480","SUP-F1":"0.749"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23600,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"RoBERTa-DenseRetriever","metrics":{"ANS-EM":"0.596","ANS-F1":"0.724","JOINT-EM":"0.345","JOINT-F1":"0.601","SUP-EM":"0.479","SUP-F1":"0.748"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23601,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"HGN + SemanticRetrievalMRS IR","metrics":{"ANS-EM":"0.567","ANS-F1":"0.692","JOINT-EM":"0.356","JOINT-F1":"0.599","SUP-EM":"0.500","SUP-F1":"0.764"},"paper_url":"https://arxiv.org/abs/1911.03631v4","paper_title":"Hierarchical Graph Network for Multi-hop Question Answering","paper_date":"2019-11-09","code_links":[{"title":"yuwfan/HGN","url":"https://github.com/yuwfan/HGN"}],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23602,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"DFGN","metrics":{"JOINT-F1":"0.5982"},"paper_url":"https://arxiv.org/abs/1905.06933v3","paper_title":"Dynamically Fused Graph Network for Multi-hop Reasoning","paper_date":"2019-05-16","code_links":[{"title":"woshiyyya/DFGN-pytorch","url":"https://github.com/woshiyyya/DFGN-pytorch"}],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23603,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"SAFSR model","metrics":{"ANS-EM":"0.589","ANS-F1":"0.716","JOINT-EM":"0.345","JOINT-F1":"0.598","SUP-EM":"0.480","SUP-F1":"0.757"},"paper_url":"http://arxiv.org/abs/1809.09600v1","paper_title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","paper_date":"2018-09-25","code_links":[{"title":"hotpotqa/hotpot","url":"https://github.com/hotpotqa/hotpot"},{"title":"mangopy/direct-rag-learning","url":"https://github.com/mangopy/direct-rag-learning"}],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23604,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"GraphRR-Fast","metrics":{"ANS-EM":"0.582","ANS-F1":"0.709","JOINT-EM":"0.310","JOINT-F1":"0.569","SUP-EM":"0.429","SUP-F1":"0.713"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23605,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"DR model","metrics":{"ANS-EM":"0.588","ANS-F1":"0.717","JOINT-EM":"0.293","JOINT-F1":"0.568","SUP-EM":"0.416","SUP-F1":"0.725"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23606,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"Quark + SemanticRetrievalMRS IR","metrics":{"ANS-EM":"0.555","ANS-F1":"0.675","JOINT-EM":"0.329","JOINT-F1":"0.562","SUP-EM":"0.456","SUP-F1":"0.730"},"paper_url":"https://arxiv.org/abs/2004.06753v1","paper_title":"A Simple Yet Strong Pipeline for HotpotQA","paper_date":"2020-04-14","code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23607,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"GAR-BERT","metrics":{"ANS-EM":"0.523","ANS-F1":"0.648","JOINT-EM":"0.330","JOINT-F1":"0.561","SUP-EM":"0.490","SUP-F1":"0.747"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23608,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"Graph-based Recurrent Retriever","metrics":{"ANS-EM":"0.560","ANS-F1":"0.689","JOINT-EM":"0.292","JOINT-F1":"0.553","SUP-EM":"0.441","SUP-F1":"0.730"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23609,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"MIR+EPS+BERT","metrics":{"ANS-EM":"0.529","ANS-F1":"0.648","JOINT-EM":"0.312","JOINT-F1":"0.548","SUP-EM":"0.428","SUP-F1":"0.720"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23610,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"GAR","metrics":{"ANS-EM":"0.482","ANS-F1":"0.613","JOINT-EM":"0.306","JOINT-F1":"0.530","SUP-EM":"0.483","SUP-F1":"0.739"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23611,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"Transformer-XH-final","metrics":{"ANS-EM":"0.516","ANS-F1":"0.641","JOINT-EM":"0.261","JOINT-F1":"0.513","SUP-EM":"0.409","SUP-F1":"0.714"},"paper_url":"https://openreview.net/forum?id=r1eIiCNYwS","paper_title":"Transformer-XH: Multi-Evidence Reasoning with eXtra Hop Attention","paper_date":"2020-05-01","code_links":[{"title":"microsoft/Transformer-XH","url":"https://github.com/microsoft/Transformer-XH"}],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23612,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"Transformer-XH","metrics":{"ANS-EM":"0.490","ANS-F1":"0.608","JOINT-EM":"0.271","JOINT-F1":"0.496","SUP-EM":"0.417","SUP-F1":"0.700"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23613,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"SemanticRetrievalMRS","metrics":{"ANS-EM":"0.453","ANS-F1":"0.573","JOINT-EM":"0.251","JOINT-F1":"0.476","SUP-EM":"0.387","SUP-F1":"0.708"},"paper_url":"https://arxiv.org/abs/1909.08041v1","paper_title":"Revealing the Importance of Semantic Retrieval for Machine Reading at Scale","paper_date":"2019-09-17","code_links":[{"title":"easonnie/semanticRetrievalMRS","url":"https://github.com/easonnie/semanticRetrievalMRS"},{"title":"dujiaxin/semanticRetrievalMRS","url":"https://github.com/dujiaxin/semanticRetrievalMRS"}],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23614,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"DrKIT","metrics":{"ANS-EM":"0.421","ANS-F1":"0.517","JOINT-EM":"0.247","JOINT-F1":"0.429","SUP-EM":"0.371","SUP-F1":"0.598"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23615,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"Entity-centric BERT Pipeline","metrics":{"ANS-EM":"0.418","ANS-F1":"0.531","JOINT-EM":"0.170","JOINT-F1":"0.392","SUP-EM":"0.263","SUP-F1":"0.573"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23616,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"PR-Bert","metrics":{"ANS-EM":"0.433","ANS-F1":"0.538","JOINT-EM":"0.145","JOINT-F1":"0.391","SUP-EM":"0.219","SUP-F1":"0.596"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23617,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"GoldEn Retriever","metrics":{"ANS-EM":"0.379","ANS-F1":"0.486","JOINT-EM":"0.180","JOINT-F1":"0.391","SUP-EM":"0.307","SUP-F1":"0.642"},"paper_url":"https://arxiv.org/abs/1910.07000v1","paper_title":"Answering Complex Open-domain Questions Through Iterative Query Generation","paper_date":"2019-10-15","code_links":[{"title":"qipeng/golden-retriever","url":"https://github.com/qipeng/golden-retriever"}],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23618,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"SAFSr-Bert","metrics":{"ANS-EM":"0.394","ANS-F1":"0.514","JOINT-EM":"0.133","JOINT-F1":"0.370","SUP-EM":"0.242","SUP-F1":"0.585"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23619,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"Cognitive Graph QA","metrics":{"ANS-EM":"0.371","ANS-F1":"0.489","JOINT-EM":"0.124","JOINT-F1":"0.349","SUP-EM":"0.228","SUP-F1":"0.577"},"paper_url":"https://arxiv.org/abs/1905.05460v2","paper_title":"Cognitive Graph for Multi-Hop Reading Comprehension at Scale","paper_date":"2019-05-14","code_links":[{"title":"THUDM/CogQA","url":"https://github.com/THUDM/CogQA"},{"title":"ShaoaAllen/CogQA","url":"https://github.com/ShaoaAllen/CogQA"}],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23620,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"GAR-NOSF","metrics":{"ANS-EM":"0.475","ANS-F1":"0.606","JOINT-EM":"0.049","JOINT-F1":"0.334","SUP-EM":"0.076","SUP-F1":"0.448"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23621,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"IKFGraph","metrics":{"ANS-EM":"0.358","ANS-F1":"0.453","JOINT-EM":"0.115","JOINT-F1":"0.304","SUP-EM":"0.160","SUP-F1":"0.512"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23622,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"AnonymousQ","metrics":{"ANS-EM":"0.369","ANS-F1":"0.460","JOINT-EM":"0.115","JOINT-F1":"0.291","SUP-EM":"0.153","SUP-F1":"0.468"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23623,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"HGN Model-reproduce","metrics":{"ANS-EM":"0.335","ANS-F1":"0.427","JOINT-EM":"0.110","JOINT-F1":"0.284","SUP-EM":"0.156","SUP-F1":"0.493"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23624,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"MUPPET","metrics":{"ANS-EM":"0.306","ANS-F1":"0.403","JOINT-EM":"0.109","JOINT-F1":"0.270","SUP-EM":"0.167","SUP-F1":"0.473"},"paper_url":"https://arxiv.org/abs/1906.06606v1","paper_title":"Multi-Hop Paragraph Retrieval for Open-Domain Question Answering","paper_date":"2019-06-15","code_links":[{"title":"yairf11/MUPPET","url":"https://github.com/yairf11/MUPPET"}],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23625,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"GRN + BERT","metrics":{"ANS-EM":"0.299","ANS-F1":"0.391","JOINT-EM":"0.083","JOINT-F1":"0.258","SUP-EM":"0.132","SUP-F1":"0.497"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23626,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"Entity-centric IR","metrics":{"ANS-EM":"0.354","ANS-F1":"0.463","JOINT-EM":"0.000","JOINT-F1":"0.255","SUP-EM":"0.001","SUP-F1":"0.432"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23627,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"KGNN","metrics":{"ANS-EM":"0.277","ANS-F1":"0.372","JOINT-EM":"0.070","JOINT-F1":"0.247","SUP-EM":"0.127","SUP-F1":"0.472"},"paper_url":"https://arxiv.org/abs/1911.02170v1","paper_title":"Multi-Paragraph Reasoning with Knowledge-enhanced Graph Neural Network","paper_date":"2019-11-06","code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23628,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"SAQA","metrics":{"ANS-EM":"0.284","ANS-F1":"0.386","JOINT-EM":"0.086","JOINT-F1":"0.245","SUP-EM":"0.147","SUP-F1":"0.472"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23629,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"GRN","metrics":{"ANS-EM":"0.273","ANS-F1":"0.365","JOINT-EM":"0.074","JOINT-F1":"0.236","SUP-EM":"0.122","SUP-F1":"0.488"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23630,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"QFE","metrics":{"ANS-EM":"0.287","ANS-F1":"0.381","JOINT-EM":"0.087","JOINT-F1":"0.231","SUP-EM":"0.142","SUP-F1":"0.444"},"paper_url":"https://arxiv.org/abs/1905.08511v2","paper_title":"Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction","paper_date":"2019-05-21","code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23631,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"SAFSr_model","metrics":{"ANS-EM":"0.289","ANS-F1":"0.391","JOINT-EM":"0.041","JOINT-F1":"0.209","SUP-EM":"0.080","SUP-F1":"0.406"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23632,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"SuppBERT","metrics":{"ANS-EM":"0.236","ANS-F1":"0.320","JOINT-EM":"0.033","JOINT-F1":"0.175","SUP-EM":"0.056","SUP-F1":"0.400"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23633,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"Baseline Model","metrics":{"ANS-EM":"0.240","ANS-F1":"0.329","JOINT-EM":"0.019","JOINT-F1":"0.162","SUP-EM":"0.039","SUP-F1":"0.377"},"paper_url":"http://arxiv.org/abs/1809.09600v1","paper_title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","paper_date":"2018-09-25","code_links":[{"title":"hotpotqa/hotpot","url":"https://github.com/hotpotqa/hotpot"},{"title":"mangopy/direct-rag-learning","url":"https://github.com/mangopy/direct-rag-learning"}],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23634,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"tes","metrics":{"ANS-EM":"0.074","ANS-F1":"0.121","JOINT-EM":"0.000","JOINT-F1":"0.011","SUP-EM":"0.000","SUP-F1":"0.078"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23635,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"PromptRank-fewshot-2-demo","metrics":{"ANS-EM":"0.581","ANS-F1":"0.711","JOINT-EM":"0.000","JOINT-F1":"0.000","SUP-EM":"0.000","SUP-F1":"0.000"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23636,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"graph-recurrent-retriever+roberta-base w. S/R-pretraining","metrics":{"ANS-EM":"0.581","ANS-F1":"0.710","JOINT-EM":"0.000","JOINT-F1":"0.000","SUP-EM":"0.000","SUP-F1":"0.000"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23637,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"TPReasoner w/o BERT","metrics":{"ANS-EM":"0.360","ANS-F1":"0.474","JOINT-EM":"0.000","JOINT-F1":"0.000","SUP-EM":"0.000","SUP-F1":"0.000"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23638,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"MultiQA","metrics":{"ANS-EM":"0.307","ANS-F1":"0.402","JOINT-EM":"0.000","JOINT-F1":"0.000","SUP-EM":"0.000","SUP-F1":"0.000"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23639,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"DecompRC","metrics":{"ANS-EM":"0.300","ANS-F1":"0.407","JOINT-EM":"0.000","JOINT-F1":"0.000","SUP-EM":"0.000","SUP-F1":"0.000"},"paper_url":"https://arxiv.org/abs/1906.02916v2","paper_title":"Multi-hop Reading Comprehension through Question Decomposition and Rescoring","paper_date":"2019-06-07","code_links":[{"title":"shmsw25/DecompRC","url":"https://github.com/shmsw25/DecompRC"},{"title":"aaronbae/AnaQA","url":"https://github.com/aaronbae/AnaQA"}],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23640,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":null,"metrics":{"ANS-EM":"0.300","ANS-F1":"0.407","JOINT-EM":"0.000","JOINT-F1":"0.000","SUP-EM":"0.000","SUP-F1":"0.000"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23641,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"Mistral multi hop with very large sources","metrics":{"ANS-EM":"0.080","ANS-F1":"0.221","JOINT-EM":"0.000","JOINT-F1":"0.000","SUP-EM":"0.000","SUP-F1":"0.000"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"JOINT-F1\", \"ANS-EM\", \"ANS-F1\", \"SUP-EM\", \"SUP-F1\", \"JOINT-EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":759331,"task":"Question Answering","parent_task":null,"dataset":"HotpotQA","model_name":"EviNote-RAG","metrics":{"ANS-F1":"0.093"},"paper_url":"https://paperswithcode.com/paper/evinote-rag-enhancing-rag-models-via-answer-supportive-evidence-notes","paper_title":"EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notes","paper_date":"2025-08-31","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]}]}