{"id":"https://openalex.org/W7204862779","doi":"https://doi.org/10.18653/2026.findings-emnlp.526","title":"CoVA-SFT: A Large-Scale Dataset for Chain of Visual Abstractions","display_name":"CoVA-SFT: A Large-Scale Dataset for Chain of Visual Abstractions","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204862779","doi":"https://doi.org/10.18653/2026.findings-emnlp.526"},"language":"en","primary_location":{"id":"doi:10.18653/2026.findings-emnlp.526","doi":"https://doi.org/10.18653/2026.findings-emnlp.526","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.526","pdf_url":"https://aclanthology.org/2026.findings-emnlp.526.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"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: EMNLP 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-emnlp.526.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139772548","display_name":"Tsung-Han Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tsung-Han Wu","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148834327","display_name":"Heekyung Lee","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heekyung Lee","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009236614","display_name":"Anya Ji","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anya Ji","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114973755","display_name":"Haoming Chen","orcid":"https://orcid.org/0009-0006-1905-3913","observed_orcids":["https://orcid.org/0009-0006-1905-3913"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoming Chen","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127844964","display_name":"Trevor Darrell","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevor Darrell","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072427753","display_name":"Joseph E. Gonzalez","orcid":"https://orcid.org/0000-0003-2921-956X","observed_orcids":["https://orcid.org/0000-0003-2921-956X"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph E. Gonzalez","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104260047","display_name":"David M. Chan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David M. Chan","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7049392,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11036","last_page":"11051"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9970999956130981,"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":0.9970999956130981,"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":0.001500000013038516,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0003000000142492354,"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/chain-of-thought-reasoning","display_name":"chain-of-thought reasoning","score":0.9819999933242798},{"id":"https://openalex.org/keywords/visual-abstraction","display_name":"visual abstraction","score":0.8209999799728394},{"id":"https://openalex.org/keywords/multimodal-reasoning","display_name":"multimodal reasoning","score":0.7630000114440918},{"id":"https://openalex.org/keywords/dataset-construction","display_name":"dataset construction","score":0.5180000066757202},{"id":"https://openalex.org/keywords/multimodal-language-models","display_name":"multimodal language models","score":0.6769999861717224},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.6060000061988831},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.4429999887943268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8393999934196472},{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.8039000034332275},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.762499988079071},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5393999814987183},{"id":"https://openalex.org/C58581272","wikidata":"https://www.wikidata.org/wiki/Q12741163","display_name":"Workspace","level":3,"score":0.5379999876022339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5360000133514404},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.532800018787384},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47380000352859497},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.4724999964237213},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3382999897003174},{"id":"https://openalex.org/C99740376","wikidata":"https://www.wikidata.org/wiki/Q17092520","display_name":"Interactive visual analysis","level":4,"score":0.33640000224113464},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.28940001130104065},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2721000015735626},{"id":"https://openalex.org/C146834321","wikidata":"https://www.wikidata.org/wiki/Q2979672","display_name":"Closure (psychology)","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.findings-emnlp.526","doi":"https://doi.org/10.18653/2026.findings-emnlp.526","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.526","pdf_url":"https://aclanthology.org/2026.findings-emnlp.526.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"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: EMNLP 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.28958","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28958","pdf_url":"https://arxiv.org/pdf/2608.28958","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.28958","doi":"https://doi.org/10.48550/arxiv.2608.28958","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.28958","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":"doi:10.18653/2026.findings-emnlp.526","doi":"https://doi.org/10.18653/2026.findings-emnlp.526","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.526","pdf_url":"https://aclanthology.org/2026.findings-emnlp.526.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"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: EMNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"},{"id":"https://openalex.org/F4320307894","display_name":"Accenture","ror":"https://ror.org/013g16z83"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204862779.pdf","grobid_xml":"https://content.openalex.org/works/W7204862779.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7106689430","https://openalex.org/W4414427071","https://openalex.org/W7164016734","https://openalex.org/W7163208587","https://openalex.org/W7160207210","https://openalex.org/W7103983983","https://openalex.org/W7118481222","https://openalex.org/W6948031217","https://openalex.org/W4415799075","https://openalex.org/W4416947266"],"abstract_inverted_index":{"Chain-of-thought":[0],"(CoT)":[1],"reasoning":[2,67,86],"has":[3],"dramatically":[4],"improved":[5],"large":[6],"language":[7,126],"models":[8,29,54,127,140],"(LLMs)":[9],"by":[10,137,149],"allowing":[11],"them":[12],"to":[13,30,40,52,56,128],"decompose":[14],"problems":[15,33],"into":[16,34],"intermediate":[17],"steps.While":[18],"CoT":[19,27,147,165],"is":[20],"widely":[21],"effective":[22],"for":[23,111,170],"linguistic":[24],"tasks,":[25,96],"text-only":[26,164],"forces":[28],"serialize":[31],"visual":[32,42,61,132],"awkward":[35],"prose.Although":[36],"architectural":[37],"solutions":[38],"exist":[39],"process":[41],"inputs,":[43],"the":[44,108,135],"community":[45],"lacks":[46],"a":[47,75,99],"massive,":[48],"multi-step,":[49],"self-corrected":[50],"dataset":[51,136],"teach":[53],"how":[55],"build":[57],"and":[58,93,97,120,131],"maintain":[59],"internal":[60],"workspaces":[62],"when":[63],"solving":[64],"purely":[65],"textual":[66],"problems.To":[68],"address":[69],"this":[70],"limitation,":[71],"we":[72],"introduce":[73],"CoVA-SFT,":[74],"highly":[76],"structured":[77],"corpus":[78],"of":[79,102,162],"51.9K":[80],"samples":[81,106],"containing":[82],"over":[83],"222K":[84],"multimodal":[85,125],"steps":[87],"across":[88],"5":[89],"distinct":[90],"layout":[91],"families":[92],"17":[94],"complex":[95],"CoVA-Bench,":[98,156],"companion":[100],"benchmark":[101],"1,700":[103],"held-out":[104],"test":[105],"spanning":[107],"same":[109],"tasks":[110],"reproducible":[112],"evaluation.By":[113],"providing":[114],"explicit":[115],"rationale":[116],"formulations,":[117],"agentic":[118],"renderings,":[119],"verification":[121],"loops,":[122],"CoVA-SFT":[123,143],"teaches":[124],"interleave":[129],"text":[130],"abstractions.We":[133],"validate":[134],"demonstrating":[138],"that":[139],"fine-tuned":[141],"on":[142,153,155],"outperform":[144],"all":[145],"interleaved":[146],"baselines":[148],"more":[150],"than":[151],"2\u00d7":[152],"average":[154],"though":[157],"they":[158],"still":[159],"fall":[160],"short":[161],"strong":[163],"baselines,":[166],"highlighting":[167],"open":[168],"challenges":[169],"future":[171],"work.":[172]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-09-02T00:00:00"}