{"id":"https://openalex.org/W3153722882","doi":"https://doi.org/10.18653/v1/2021.emnlp-main.700","title":"Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability","display_name":"Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3153722882","doi":"https://doi.org/10.18653/v1/2021.emnlp-main.700","mag":"3153722882"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.700","pdf_url":"https://aclanthology.org/2021.emnlp-main.700.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2021.emnlp-main.700.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101400717","display_name":"Xin Lv","orcid":"https://orcid.org/0000-0002-4843-7987"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Lv","raw_affiliation_strings":["Department of Computer Science and Technology, BNRist","KIRC, Institute for Artificial Intelligence, Tsinghua University, Beijing 100084, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist","institution_ids":[]},{"raw_affiliation_string":"KIRC, Institute for Artificial Intelligence, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013247988","display_name":"Yixin Cao","orcid":"https://orcid.org/0000-0002-6927-438X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Yixin Cao","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060498828","display_name":"Lei Hou","orcid":"https://orcid.org/0000-0002-8907-3526"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Hou","raw_affiliation_strings":["Department of Computer Science and Technology, BNRist","KIRC, Institute for Artificial Intelligence, Tsinghua University, Beijing 100084, China"],"affiliations":[{"raw_affiliation_string":"KIRC, Institute for Artificial Intelligence, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003324011","display_name":"Juanzi Li","orcid":"https://orcid.org/0000-0002-6244-0664"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juanzi Li","raw_affiliation_strings":["Department of Computer Science and Technology, BNRist","KIRC, Institute for Artificial Intelligence, Tsinghua University, Beijing 100084, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist","institution_ids":[]},{"raw_affiliation_string":"KIRC, Institute for Artificial Intelligence, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320723","display_name":"Zhiyuan Liu","orcid":"https://orcid.org/0000-0002-7709-2543"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Liu","raw_affiliation_strings":["Department of Computer Science and Technology, BNRist","KIRC, Institute for Artificial Intelligence, Tsinghua University, Beijing 100084, China"],"affiliations":[{"raw_affiliation_string":"KIRC, Institute for Artificial Intelligence, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100444188","display_name":"Yichi Zhang","orcid":"https://orcid.org/0000-0002-4292-6835"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichi Zhang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072052633","display_name":"Zelin Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zelin Dai","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013247988"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.915,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":9,"citation_normalized_percentile":{"value":0.756396,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":86,"max":87},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9979,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9979,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9976,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9876,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.9884873},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.78913414},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6877867}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9884873},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.78913414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.69818836},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6877867},{"id":"https://openalex.org/C25906391","wikidata":"https://www.wikidata.org/wiki/Q1432381","display_name":"Hop (telecommunications)","level":2,"score":0.57720655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5568665},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.524916},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34685624},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.700","pdf_url":"https://aclanthology.org/2021.emnlp-main.700.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/7317","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":["Singapore Management University"],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2104.06751","pdf_url":"https://arxiv.org/pdf/2104.06751","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.700","pdf_url":"https://aclanthology.org/2021.emnlp-main.700.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":29,"referenced_works":["https://openalex.org/W2080133951","https://openalex.org/W2107306718","https://openalex.org/W2127795553","https://openalex.org/W2250635077","https://openalex.org/W2728059831","https://openalex.org/W2769099080","https://openalex.org/W2807015674","https://openalex.org/W2808051209","https://openalex.org/W2885711033","https://openalex.org/W2889344053","https://openalex.org/W2898632797","https://openalex.org/W2952927816","https://openalex.org/W2962886429","https://openalex.org/W2963425543","https://openalex.org/W2964072618","https://openalex.org/W2964116313","https://openalex.org/W2964194917","https://openalex.org/W2966298461","https://openalex.org/W2970485665","https://openalex.org/W2970618565","https://openalex.org/W2971038186","https://openalex.org/W2987200109","https://openalex.org/W2997463623","https://openalex.org/W3034903373","https://openalex.org/W3035251962","https://openalex.org/W3041492656","https://openalex.org/W3098682001","https://openalex.org/W3100187427","https://openalex.org/W3104992282"],"related_works":["https://openalex.org/W4386025632","https://openalex.org/W4385965371","https://openalex.org/W4385957992","https://openalex.org/W4381245711","https://openalex.org/W4302612983","https://openalex.org/W4287077734","https://openalex.org/W4229079080","https://openalex.org/W4206534706","https://openalex.org/W2950577464","https://openalex.org/W2593649365"],"abstract_inverted_index":{"Multi-hop":[0],"reasoning":[1,56,134,158,184],"has":[2,33],"been":[3,34],"widely":[4],"studied":[5],"in":[6,18,160],"recent":[7],"years":[8],"to":[9,49,60,85,168,176],"obtain":[10],"more":[11],"interpretable":[12],"link":[13],"prediction.":[14],"However,":[15],"we":[16,44,66,107,115],"find":[17],"experiments":[19],"that":[20,128],"many":[21],"paths":[22],"given":[23,147],"by":[24,148],"these":[25,87],"models":[26,57,135,154,159],"are":[27],"actually":[28],"unreasonable,":[29],"while":[30],"little":[31],"work":[32],"done":[35],"on":[36,120],"interpretability":[37,53,77,91,130],"evaluation":[38],"for":[39,78,171],"them.":[40],"In":[41,64,105],"this":[42],"paper,":[43],"propose":[45],"a":[46,103,169],"unified":[47],"framework":[48],"quantitatively":[50],"evaluate":[51],"the":[52,90,109,124,129,144,152,156,182],"of":[54,93,111,131,162],"multi-hop":[55,133,157,183],"so":[58],"as":[59],"advance":[61],"their":[62],"development.":[63],"specific,":[65],"define":[67],"three":[68],"metrics,":[69],"including":[70],"path":[71],"recall,":[72],"local":[73],"interpretability,":[74,165],"and":[75,80,101,123,139,164,191],"global":[76],"evaluation,":[79],"design":[81],"an":[82],"approximate":[83],"strategy":[84],"calculate":[86],"metrics":[88],"using":[89],"scores":[92],"rules.":[94],"We":[95,186],"manually":[96],"annotate":[97],"all":[98],"possible":[99],"rules":[100],"establish":[102],"benchmark.":[104,113,150],"experiments,":[106],"verify":[108],"effectiveness":[110],"our":[112,121,149,189],"Besides,":[114],"run":[116],"nine":[117],"representative":[118],"baselines":[119],"benchmark,":[122],"experimental":[125],"results":[126],"show":[127],"current":[132],"is":[136,140],"less":[137],"satisfactory":[138],"51.7%":[141],"lower":[142],"than":[143],"upper":[145],"bound":[146],"Moreover,":[151],"rule-based":[153],"outperform":[155],"terms":[161],"performance":[163],"which":[166],"points":[167],"direction":[170],"future":[172],"research,":[173],"i.e.,":[174],"how":[175],"better":[177],"incorporate":[178],"rule":[179],"information":[180],"into":[181],"model.":[185],"will":[187],"publish":[188],"codes":[190],"datasets":[192],"upon":[193],"acceptance.":[194]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3153722882","counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2024-12-31T00:20:28.229671","created_date":"2021-04-26"}