{"id":"https://openalex.org/W4415795341","doi":"https://doi.org/10.52202/079017-3773","title":"SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers","display_name":"SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4415795341","doi":"https://doi.org/10.52202/079017-3773"},"language":"en","primary_location":{"id":"doi:10.52202/079017-3773","doi":"https://doi.org/10.52202/079017-3773","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-3773","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.09413","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067636415","display_name":"Shraman Pramanick","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shraman Pramanick","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102762707","display_name":"Rama Chellappa","orcid":"https://orcid.org/0000-0002-7638-1650","observed_orcids":["https://orcid.org/0000-0002-7638-1650"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rama Chellappa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5025689655","display_name":"Subhashini Venugopalan","orcid":"https://orcid.org/0000-0003-3729-8456","observed_orcids":["https://orcid.org/0000-0003-3729-8456"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Subhashini Venugopalan","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":4.4769,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.96348326,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"118807","last_page":"118833"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9965999722480774,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9965999722480774,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.00039999998989515007,"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/T10028","display_name":"Topic Modeling","score":0.00019999999494757503,"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/multimodal-question-answering","display_name":"multimodal question answering","score":0.9760000109672546},{"id":"https://openalex.org/keywords/scientific-publications","display_name":"scientific publications","score":0.9900000095367432},{"id":"https://openalex.org/keywords/datasets","display_name":"datasets","score":0.3630000054836273},{"id":"https://openalex.org/keywords/question-answering-evaluation","display_name":"question answering evaluation","score":0.3720000088214874}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6622999906539917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6284999847412109},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4106000065803528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3935999870300293},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3882000148296356},{"id":"https://openalex.org/C3019144022","wikidata":"https://www.wikidata.org/wiki/Q4124998","display_name":"Questions and answers","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2475000023841858},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2409999966621399}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/079017-3773","doi":"https://doi.org/10.52202/079017-3773","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-3773","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2407.09413","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.09413","pdf_url":"https://arxiv.org/pdf/2407.09413","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2407.09413","doi":"https://doi.org/10.48550/arxiv.2407.09413","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.09413","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.09413","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.09413","pdf_url":"https://arxiv.org/pdf/2407.09413","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415795341.pdf","grobid_xml":"https://content.openalex.org/works/W4415795341.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7127132348","https://openalex.org/W4400517453","https://openalex.org/W4394625790","https://openalex.org/W7214777218","https://openalex.org/W4412887783","https://openalex.org/W7106811227","https://openalex.org/W4417058139","https://openalex.org/W7197052418","https://openalex.org/W4412944054","https://openalex.org/W4407765080"],"abstract_inverted_index":{"Seeking":[0],"answers":[1],"to":[2,57,89,98,154],"questions":[3,128],"within":[4,63],"long":[5],"scientific":[6,30,67,212],"research":[7,68,160,201],"articles":[8,69],"is":[9],"a":[10,165],"crucial":[11],"area":[12],"of":[13,66,73,79,83,150,159,188],"study":[14],"that":[15,112,173],"aids":[16],"readers":[17],"in":[18,34],"quickly":[19],"addressing":[20],"their":[21],"inquiries.":[22],"However,":[23],"existing":[24],"question-answering":[25],"(QA)":[26],"datasets":[27],"based":[28],"on":[29,39,107,206],"papers":[31],"are":[32],"limited":[33],"scale":[35],"and":[36,61,81,95,110,122,133,178,202],"focus":[37],"solely":[38],"textual":[40,193],"content.":[41],"We":[42,102,182],"introduce":[43],"SPIQA":[44,125],"(Scientific":[45],"Paper":[46],"Image":[47],"Question":[48],"Answering),":[49],"the":[50,64,77,100,148,156,185,203],"first":[51],"large-scale":[52],"QA":[53],"dataset":[54],"specifically":[55],"designed":[56],"interpret":[58],"complex":[59],"figures":[60],"tables":[62],"context":[65],"across":[70],"various":[71],"domains":[72],"computer":[74],"science.":[75],"Leveraging":[76],"breadth":[78],"expertise":[80],"ability":[82,149],"multimodal":[84,152],"large":[85],"language":[86],"models":[87],"(MLLMs)":[88],"understand":[90],"figures,":[91],"we":[92,146,163,209],"employ":[93],"automatic":[94],"manual":[96],"curation":[97],"create":[99],"dataset.":[101],"craft":[103],"an":[104],"information-seeking":[105],"task":[106],"interleaved":[108],"images":[109,115],"text":[111],"involves":[113],"multiple":[114],"covering":[116],"plots,":[117],"charts,":[118],"tables,":[119],"schematic":[120],"diagrams,":[121],"result":[123],"visualizations.":[124],"comprises":[126],"270K":[127],"divided":[129],"into":[130],"training,":[131],"validation,":[132],"three":[134],"different":[135],"evaluation":[136,168],"splits.":[137],"Through":[138],"extensive":[139],"experiments":[140],"with":[141,170,191,211],"12":[142],"prominent":[143],"foundational":[144],"models,":[145],"evaluate":[147],"current":[151],"systems":[153],"comprehend":[155],"nuanced":[157],"aspects":[158],"articles.":[161],"Additionally,":[162],"propose":[164],"Chain-of-Thought":[166],"(CoT)":[167],"strategy":[169],"in-context":[171],"retrieval":[172],"allows":[174],"fine-grained,":[175],"step-by-step":[176],"assessment":[177],"improves":[179],"model":[180],"performance.":[181],"further":[183],"explore":[184],"upper":[186],"bounds":[187],"performance":[189],"enhancement":[190],"additional":[192],"information,":[194],"highlighting":[195],"its":[196],"promising":[197],"potential":[198],"for":[199],"future":[200],"dataset's":[204],"impact":[205],"revolutionizing":[207],"how":[208],"interact":[210],"literature.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-11-03T00:00:00"}