{"id":"https://openalex.org/W3021358742","doi":null,"title":"Measuring and Reducing Non-Multifact Reasoning in Multi-hop Question Answering.","display_name":"Measuring and Reducing Non-Multifact Reasoning in Multi-hop Question Answering.","publication_year":2020,"publication_date":"2020-05-02","ids":{"openalex":"https://openalex.org/W3021358742","mag":"3021358742"},"language":"en","primary_location":{"id":"mag:3021358742","doi":null,"is_oa":false,"landing_page_url":"http://export.arxiv.org/pdf/2005.00789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025500234","display_name":"Harsh K. Trivedi","orcid":"https://orcid.org/0000-0003-1603-8591","observed_orcids":["https://orcid.org/0000-0003-1603-8591"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harsh Trivedi","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1603-8591","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101768349","display_name":"Niranjan Balasubramanian","orcid":"https://orcid.org/0000-0003-4187-9368","observed_orcids":["https://orcid.org/0000-0003-4187-9368"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niranjan Balasubramanian","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4187-9368","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033257344","display_name":"Tushar Khot","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tushar Khot","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5077726785","display_name":"Ashish Sabharwal","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashish Sabharwal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0837,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39968171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9535999894142151,"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/T10028","display_name":"Topic Modeling","score":0.9535999894142151,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.022299999371170998,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.009600000455975533,"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/multi-hop-question-answering","display_name":"multi-hop question answering","score":0.9570000171661377},{"id":"https://openalex.org/keywords/xlnet","display_name":"XLNet","score":0.7250000238418579}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7692005634307861},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7523780465126038},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7269608974456787},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4925409257411957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47057291865348816},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4679984450340271},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34346604347229004},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29353067278862},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07667922973632812},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3021358742","doi":null,"is_oa":false,"landing_page_url":"http://export.arxiv.org/pdf/2005.00789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2790415926","https://openalex.org/W2793978524","https://openalex.org/W2890894339","https://openalex.org/W2942128719","https://openalex.org/W2950618399","https://openalex.org/W2950813464","https://openalex.org/W2951328433","https://openalex.org/W2951862794","https://openalex.org/W2953163841","https://openalex.org/W2963323070","https://openalex.org/W2963341956","https://openalex.org/W2963969878","https://openalex.org/W2987215000","https://openalex.org/W2987553933","https://openalex.org/W2996848635","https://openalex.org/W2997759614","https://openalex.org/W3014564055","https://openalex.org/W3015468748","https://openalex.org/W3017192286","https://openalex.org/W3105055324"],"related_works":["https://openalex.org/W3087107227","https://openalex.org/W4386576886","https://openalex.org/W3190126809","https://openalex.org/W2979196189","https://openalex.org/W4287083780","https://openalex.org/W2951328433","https://openalex.org/W7213417024","https://openalex.org/W7214928833","https://openalex.org/W3115947671","https://openalex.org/W6910694488"],"abstract_inverted_index":{"The":[0],"measurement":[1],"of":[2,15,49,67,79,97,146],"true":[3],"progress":[4],"in":[5,149,169],"multihop":[6,51],"question-answering":[7],"has":[8],"been":[9],"muddled":[10],"by":[11,152],"the":[12,27,34,40,43,47,138,144],"strong":[13],"ability":[14],"models":[16],"to":[17,108,158,172],"exploit":[18],"artifacts":[19],"and":[20,30,70,122],"other":[21],"reasoning":[22,69,148],"shortcuts.":[23],"Models":[24],"can":[25,112],"produce":[26],"correct":[28],"answer,":[29],"even":[31],"independently":[32],"identify":[33],"supporting":[35,98],"facts,":[36,99],"without":[37],"necessarily":[38],"connecting":[39],"information":[41],"between":[42],"facts.":[44],"This":[45],"defeats":[46],"purpose":[48],"building":[50],"QA":[52],"datasets.":[53],"We":[54],"make":[55],"three":[56],"contributions":[57],"towards":[58],"addressing":[59],"this":[60,65,83,150],"issue.":[61],"First,":[62],"we":[63,85,104,127],"formalize":[64],"form":[66],"disconnected":[68,101],"propose":[71],"contrastive":[72],"support":[73],"sufficiency":[74,124,139],"as":[75],"a":[76,106,113,131,161,165],"better":[77],"test":[78],"multifact":[80],"reasoning.":[81,102],"To":[82],"end,":[84],"introduce":[86],"an":[87],"automated":[88],"sufficiency-based":[89],"dataset":[90],"transformation":[91],"that":[92,137],"considers":[93],"all":[94],"possible":[95],"partitions":[96],"capturing":[100],"Second,":[103],"develop":[105],"probe":[107],"measure":[109],"how":[110],"much":[111],"model":[114,134,151,163],"cheat":[115,159],"(via":[116],"non-multifact":[117,147,162],"reasoning)":[118],"on":[119],"existing":[120],"tests":[121],"our":[123],"test.":[125],"Third,":[126],"conduct":[128],"experiments":[129],"using":[130],"transformer":[132],"based":[133],"(XLNet),":[135],"demonstrating":[136],"transform":[140],"not":[141],"only":[142],"reduces":[143],"amount":[145],"6.5%":[153],"but":[154],"is":[155],"also":[156],"harder":[157],"--":[160],"sees":[164],"20.8%":[166],"(absolute)":[167],"reduction":[168],"score":[170],"compared":[171],"previous":[173],"metrics.":[174]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2020-05-13T00:00:00"}