{"id":"https://openalex.org/W4403579191","doi":"https://doi.org/10.1109/iccv51701.2025.00312","title":"Trust but Verify: Programmatic VLM Evaluation in the Wild","display_name":"Trust but Verify: Programmatic VLM Evaluation in the Wild","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4403579191","doi":"https://doi.org/10.1109/iccv51701.2025.00312"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.13121","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110751285","display_name":"Viraj Prabhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viraj Prabhu","raw_affiliation_strings":["Salesforce AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce AI Research","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066334452","display_name":"Senthil Purushwalkam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210161460","display_name":"OpenAI (United States)","ror":"https://ror.org/05wx9n238","country_code":"US","type":"company","lineage":["https://openalex.org/I4210161460"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Senthil Purushwalkam","raw_affiliation_strings":["OpenAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OpenAI","institution_ids":["https://openalex.org/I4210161460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114337826","display_name":"An Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"An Yan","raw_affiliation_strings":["Salesforce AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce AI Research","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032046813","display_name":"Caiming Xiong","orcid":"https://orcid.org/0000-0003-0349-8628"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Caiming Xiong","raw_affiliation_strings":["Salesforce AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce AI Research","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109335573","display_name":"Ran Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ran Xu","raw_affiliation_strings":["Salesforce AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce AI Research","institution_ids":["https://openalex.org/I4210155268"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3258","last_page":"3267"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.2493000030517578,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.2493000030517578,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.37265437841415405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.37265437841415405}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.13121","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.13121","pdf_url":"https://arxiv.org/pdf/2410.13121","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.13121","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.13121","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.13121","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.13121","pdf_url":"https://arxiv.org/pdf/2410.13121","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403579191.pdf","grobid_xml":"https://content.openalex.org/works/W4403579191.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"often":[3],"generate":[4,80],"plausible":[5],"but":[6,111],"incorrect":[7],"responses":[8,22,51,121],"to":[9,23,52,79,98,117,122,167],"visual":[10],"queries.":[11,54],"However,":[12],"reliably":[13],"quantifying":[14],"the":[15,36,94,135,150,173],"effect":[16],"of":[17,108,139,153,156],"such":[18],"hallucinations":[19],"in":[20,124],"free-form":[21,119],"open-ended":[24,53],"queries":[25,123],"is":[26],"challenging":[27,110],"as":[28,85,87],"it":[29,78],"requires":[30],"visually":[31,112],"verifying":[32],"each":[33,100],"claim":[34],"within":[35,142],"response.":[37],"We":[38,103,148],"propose":[39,127],"Programmatic":[40],"VLM":[41,50],"Evaluation":[42],"(PROVE),":[43],"a":[44,60,66,72,106,128,140,143,154,169],"new":[45],"benchmarking":[46],"paradigm":[47],"for":[48],"evaluating":[49],"To":[55],"construct":[56,105],"PROVE,":[57,125,159],"we":[58,126],"provide":[59],"large":[61],"language":[62],"model":[63,120],"(LLM)":[64],"with":[65],"high-fidelity":[67],"scene-graph":[68],"representation":[69],"constructed":[70],"from":[71],"hyper-detailed":[73],"image":[74],"caption,":[75],"and":[76,137],"prompt":[77],"diverse":[81],"question-answer":[82],"(QA)":[83],"pairs,":[84],"well":[86],"programs":[88],"that":[89,132,161],"can":[90],"be":[91],"executed":[92],"over":[93],"scene":[95,145],"graph":[96],"object":[97],"verify":[99],"QA":[101,114],"pair.":[102],"thus":[104],"benchmark":[107,149],"10.5k":[109],"grounded":[113],"pairs.":[115],"Next,":[116],"evaluate":[118],"programmatic":[129],"evaluation":[130],"strategy":[131],"measures":[133],"both":[134],"helpfulness":[136],"truthfulness":[138],"response":[141],"unified":[144],"graph-based":[146],"framework.":[147],"helpfulness-truthfulness":[151],"trade-offs":[152],"range":[155],"VLMs":[157],"on":[158],"finding":[160],"very":[162],"few":[163],"are":[164],"in-fact":[165],"able":[166],"achieve":[168],"good":[170],"balance":[171],"between":[172],"two.":[174],"Project":[175],"page:":[176],"\\url{https://prove-explorer.netlify.app/}.":[177]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}