{"id":"https://openalex.org/W4402670533","doi":"https://doi.org/10.18653/v1/2024.findings-acl.885","title":"BloomVQA: Assessing Hierarchical Multi-modal Comprehension","display_name":"BloomVQA: Assessing Hierarchical Multi-modal Comprehension","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402670533","doi":"https://doi.org/10.18653/v1/2024.findings-acl.885"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.findings-acl.885","doi":"https://doi.org/10.18653/v1/2024.findings-acl.885","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.findings-acl.885","pdf_url":"https://aclanthology.org/2024.findings-acl.885.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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,"raw_source_name":"Findings of the Association for Computational Linguistics ACL 2024","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2024.findings-acl.885.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004105936","display_name":"Yunye Gong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunye Gong","raw_affiliation_strings":["SRI International"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031427851","display_name":"Robik Shrestha","orcid":"https://orcid.org/0000-0002-0945-3458","observed_orcids":["https://orcid.org/0000-0002-0945-3458"]},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robik Shrestha","raw_affiliation_strings":["Department of Computer Science , Rochester Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093557701","display_name":"Jared Claypoole","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jared Claypoole","raw_affiliation_strings":["SRI International"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052890596","display_name":"Michael Cogswell","orcid":"https://orcid.org/0000-0003-1647-0325","observed_orcids":["https://orcid.org/0000-0003-1647-0325"]},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Cogswell","raw_affiliation_strings":["SRI International"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065379518","display_name":"Arijit Ray","orcid":"https://orcid.org/0000-0002-4175-0655","observed_orcids":["https://orcid.org/0000-0002-4175-0655"]},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arijit Ray","raw_affiliation_strings":["Department of Computer Science , Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Boston University","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046979072","display_name":"Christopher Kanan","orcid":"https://orcid.org/0000-0002-6412-995X","observed_orcids":["https://orcid.org/0000-0002-6412-995X"]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Kanan","raw_affiliation_strings":["Department of Computer Science , University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028124265","display_name":"Ajay Divakaran","orcid":"https://orcid.org/0000-0003-0371-5346","observed_orcids":["https://orcid.org/0000-0003-0371-5346"]},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ajay Divakaran","raw_affiliation_strings":["SRI International"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5792,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75454224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"14905","last_page":"14918"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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":0.0,"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/visual-question-answering","display_name":"visual question answering","score":0.8360000252723694},{"id":"https://openalex.org/keywords/bloom-s-taxonomy","display_name":"Bloom's taxonomy","score":0.6100000143051147},{"id":"https://openalex.org/keywords/large-vision-language-models","display_name":"large vision-language models","score":0.796999990940094},{"id":"https://openalex.org/keywords/picture-stories","display_name":"picture stories","score":0.9020000100135803},{"id":"https://openalex.org/keywords/hierarchical-graph-representation","display_name":"hierarchical graph representation","score":0.718999981880188},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.8610000014305115},{"id":"https://openalex.org/keywords/model-consistency","display_name":"model consistency","score":0.8640000224113464},{"id":"https://openalex.org/keywords/gpt-4v","display_name":"GPT-4V","score":0.8679999709129333},{"id":"https://openalex.org/keywords/visual-grounding","display_name":"visual grounding","score":0.41499999165534973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7069530487060547},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6464939713478088},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5028709769248962},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39111974835395813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3498654365539551},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15425196290016174},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2024.findings-acl.885","doi":"https://doi.org/10.18653/v1/2024.findings-acl.885","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.findings-acl.885","pdf_url":"https://aclanthology.org/2024.findings-acl.885.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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,"raw_source_name":"Findings of the Association for Computational Linguistics ACL 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2312.12716","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.12716","pdf_url":"https://arxiv.org/pdf/2312.12716","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.2312.12716","doi":"https://doi.org/10.48550/arxiv.2312.12716","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2312.12716","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-acl.885","doi":"https://doi.org/10.18653/v1/2024.findings-acl.885","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.findings-acl.885","pdf_url":"https://aclanthology.org/2024.findings-acl.885.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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,"raw_source_name":"Findings of the Association for Computational Linguistics ACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3748439640","display_name":"RI: Small: Lifelong Multimodal Concept Learning","funder_award_id":"1909696","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7988726922","display_name":"CAREER: Brain-inspired Methods for Continual Learning of Large-scale Vision and Language Tasks","funder_award_id":"2326491","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402670533.pdf","grobid_xml":"https://content.openalex.org/works/W4402670533.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W4300978535","https://openalex.org/W4313304663","https://openalex.org/W4318718936","https://openalex.org/W4366330503","https://openalex.org/W4366850747","https://openalex.org/W4385002382","https://openalex.org/W4385292963","https://openalex.org/W4385473806","https://openalex.org/W4385988359","https://openalex.org/W4388481599","https://openalex.org/W4391136507","https://openalex.org/W4392935324","https://openalex.org/W4401043215","https://openalex.org/W4402916396"],"related_works":["https://openalex.org/W4414197755","https://openalex.org/W4403570065","https://openalex.org/W7166796127","https://openalex.org/W6941367375","https://openalex.org/W6891957660","https://openalex.org/W4408446323","https://openalex.org/W4388962926","https://openalex.org/W7165745012","https://openalex.org/W6922440477","https://openalex.org/W2950104027"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,53,67,131],"novel":[3,68,78],"VQA":[4,115],"dataset,":[5],"BloomVQA,":[6],"to":[7,66,94,111,118],"facilitate":[8],"comprehensive":[9],"evaluation":[10,85],"of":[11,45,133],"large":[12],"vision-language":[13],"models":[14,141],"on":[15,23,38,89,101,159],"comprehension":[16,105,127,149],"tasks.Unlike":[17],"current":[18],"benchmarks":[19],"that":[20,41],"often":[21],"focus":[22],"fact-based":[24],"memorization":[25],"and":[26,77,86,106,129],"simple":[27],"reasoning":[28],"tasks":[29,102],"without":[30],"theoretical":[31],"grounding,":[32],"we":[33,97],"collect":[34],"multiple-choice":[35],"samples":[36],"based":[37,158],"picture":[39],"stories":[40],"reflect":[42],"different":[43],"levels":[44,128],"comprehension,":[46],"as":[47],"laid":[48],"out":[49],"in":[50,61,114,150],"Bloom's":[51],"Taxonomy,":[52],"classic":[54],"framework":[55],"for":[56,138,156],"learning":[57],"assessment":[58],"widely":[59],"adopted":[60],"education":[62],"research.Our":[63],"data":[64,75],"maps":[65],"hierarchical":[69],"graph":[70],"representation":[71],"which":[72],"enables":[73],"automatic":[74],"augmentation":[76],"measures":[79],"characterizing":[80],"model":[81],"consistency.We":[82],"perform":[83],"graded":[84],"reliability":[87],"analysis":[88],"recent":[90],"multi-modal":[91],"models.In":[92],"comparison":[93,117],"lowlevel":[95],"tasks,":[96],"observe":[98],"decreased":[99],"performance":[100],"requiring":[103],"advanced":[104],"cognitive":[107],"skills":[108],"with":[109,147],"up":[110],"38.0%":[112],"drop":[113],"accuracy.In":[116],"earlier":[119],"models,":[120],"GPT-4V":[121],"demonstrates":[122],"improved":[123],"accuracy":[124],"over":[125],"all":[126],"shows":[130],"tendency":[132],"bypassing":[134],"visual":[135],"inputs":[136],"especially":[137],"higher-level":[139],"tasks.Current":[140],"also":[142],"show":[143],"consistency":[144],"patterns":[145],"misaligned":[146],"human":[148],"various":[151],"scenarios,":[152],"demonstrating":[153],"the":[154],"need":[155],"improvement":[157],"theoretically-grounded":[160],"criteria.The":[161],"dataset":[162],"can":[163],"be":[164],"accessed":[165],"at":[166],"https://huggingface.":[167],"co/datasets/ygong/BloomVQA.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-09-21T00:00:00"}