{"id":"https://openalex.org/W4405035698","doi":"https://doi.org/10.48550/arxiv.2412.02172","title":"VISCO: Benchmarking Fine-Grained Critique and Correction Towards Self-Improvement in Visual Reasoning","display_name":"VISCO: Benchmarking Fine-Grained Critique and Correction Towards Self-Improvement in Visual Reasoning","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4405035698","doi":"https://doi.org/10.48550/arxiv.2412.02172"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2412.02172","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.02172","pdf_url":"https://arxiv.org/pdf/2412.02172","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"},"volume":null,"type":"erratum","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.02172","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100879285","display_name":"Xueqing Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Xueqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ding, Yuheng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Yuheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Bingxuan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Bingxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100567599","display_name":"Pan Lu","orcid":"https://orcid.org/0000-0002-2193-8415","observed_orcids":["https://orcid.org/0000-0002-2193-8415"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Pan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110195053","display_name":"Da Yin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Da","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073201681","display_name":"Kai\u2010Wei Chang","orcid":"https://orcid.org/0000-0002-4991-5274","observed_orcids":["https://orcid.org/0000-0002-4991-5274"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang, Kai-Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5030248499","display_name":"Nanyun Peng","orcid":"https://orcid.org/0000-0002-8509-6595","observed_orcids":["https://orcid.org/0000-0002-8509-6595"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Nanyun","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/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/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"}},{"id":"https://openalex.org/T11010","display_name":"Logic, Reasoning, and Knowledge","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/large-vision-language-models","display_name":"large vision-language models","score":0.8309999704360962},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"visual reasoning","score":0.8130000233650208},{"id":"https://openalex.org/keywords/personal-development","display_name":"human development","score":0.8029999732971191},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.7120000123977661},{"id":"https://openalex.org/keywords/chain-of-thought","display_name":"chain-of-thought","score":0.8180000185966492},{"id":"https://openalex.org/keywords/natural-language-explanations","display_name":"natural language explanations","score":0.7480000257492065},{"id":"https://openalex.org/keywords/error-propagation","display_name":"error propagation","score":0.5680000185966492},{"id":"https://openalex.org/keywords/visual-perception","display_name":"visual perception","score":0.609000027179718}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8752862215042114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44620388746261597},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.37011802196502686},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3583945035934448},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3183009624481201},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.17326894402503967},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.06560620665550232}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2412.02172","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.02172","pdf_url":"https://arxiv.org/pdf/2412.02172","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.2412.02172","doi":"https://doi.org/10.48550/arxiv.2412.02172","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.02172","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:2412.02172","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.02172","pdf_url":"https://arxiv.org/pdf/2412.02172","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4412888604","https://openalex.org/W4416048759","https://openalex.org/W7131423640","https://openalex.org/W4414198492","https://openalex.org/W4402670898","https://openalex.org/W7133541024","https://openalex.org/W4417347847","https://openalex.org/W7164544560","https://openalex.org/W7165682374","https://openalex.org/W7155418356"],"abstract_inverted_index":{"The":[0],"ability":[1],"of":[2,25,48,78,95,111,155,176],"large":[3],"vision-language":[4],"models":[5],"(LVLMs)":[6],"to":[7,39,51,60,74,89,125,144,149,172,191],"critique":[8,44,61,130,141,145,185],"and":[9,45,69,84,122,152,186],"correct":[10],"their":[11,19,91],"reasoning":[12,64],"is":[13,30,131],"an":[14,164],"essential":[15],"building":[16],"block":[17],"towards":[18],"self-improvement.":[20],"However,":[21,115],"a":[22,56],"systematic":[23],"analysis":[24],"such":[26],"capabilities":[27,47],"in":[28,81,140,178],"LVLMs":[29,73,97],"still":[31],"lacking.":[32],"We":[33,135],"propose":[34,163],"VISCO,":[35],"the":[36,42,62,76,82,104,109,112,116,126,132,170,179],"first":[37],"benchmark":[38],"extensively":[40],"analyze":[41],"fine-grained":[43,70],"correction":[46,187],"LVLMs.":[49],"Compared":[50],"existing":[52],"work":[53],"that":[54,99,129,168],"uses":[55],"single":[57],"scalar":[58],"value":[59],"entire":[63],"[4],":[65],"VISCO":[66],"features":[67],"dense":[68],"critique,":[71],"requiring":[72],"evaluate":[75],"correctness":[77],"each":[79,174],"step":[80],"chain-of-thought":[83],"provide":[85],"natural":[86],"language":[87],"explanations":[88],"support":[90],"judgments.":[92],"Extensive":[93],"evaluation":[94],"24":[96],"demonstrates":[98],"human-written":[100],"critiques":[101,118],"significantly":[102,183],"enhance":[103],"performance":[105,188],"after":[106],"correction,":[107],"showcasing":[108],"potential":[110],"self-improvement":[113],"strategy.":[114],"model-generated":[117],"are":[119],"less":[120],"helpful":[121],"sometimes":[123],"detrimental":[124],"performance,":[127],"suggesting":[128],"crucial":[133],"bottleneck.":[134],"identified":[136],"three":[137],"common":[138],"patterns":[139],"failures:":[142],"failure":[143],"visual":[146],"perception,":[147],"reluctance":[148],"\"say":[150],"no\",":[151],"exaggerated":[153],"assumption":[154],"error":[156],"propagation.":[157],"To":[158],"address":[159],"these":[160],"issues,":[161],"we":[162],"effective":[165],"LookBack":[166,182],"strategy":[167],"revisits":[169],"image":[171],"verify":[173],"piece":[175],"information":[177],"initial":[180],"reasoning.":[181],"improves":[184],"by":[189],"up":[190],"13.5%.":[192]},"counts_by_year":[],"updated_date":"2026-09-27T08:07:27.782135","created_date":"2024-12-06T00:00:00"}
