{"id":"https://openalex.org/W7160119641","doi":"https://doi.org/10.63317/28jn9v88qbod","title":"VG-CoT: Towards Trustworthy Visual Reasoning via Grounded Chain-of-Thought","display_name":"VG-CoT: Towards Trustworthy Visual Reasoning via Grounded Chain-of-Thought","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W7160119641","doi":"https://doi.org/10.63317/28jn9v88qbod"},"language":null,"primary_location":{"id":"doi:10.63317/28jn9v88qbod","is_oa":false,"landing_page_url":"https://doi.org/10.63317/28jn9v88qbod","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2604.21396","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111275032","display_name":"Byeonggeuk Lim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Byeonggeuk Lim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134558795","display_name":"Kyeonghyun Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyeonghyun Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135242185","display_name":"Jungmin Yun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jungmin Yun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135172007","display_name":"Youngbin Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Youngbin Kim","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48531792,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11108","last_page":"11118"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.23229999840259552,"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/T10799","display_name":"Data Visualization and Analytics","score":0.23229999840259552,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2020999938249588,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.10649999976158142,"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/trustworthiness","display_name":"Trustworthiness","score":0.51910001039505},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.35249999165534973},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.3100999891757965},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.2906000018119812},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.28999999165534973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5468999743461609},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.51910001039505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3939000070095062},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3790999948978424},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3603000044822693},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3343999981880188},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.2721000015735626},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2524000108242035}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.63317/28jn9v88qbod","is_oa":false,"landing_page_url":"https://doi.org/10.63317/28jn9v88qbod","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2604.21396","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.21396","pdf_url":"https://arxiv.org/pdf/2604.21396","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,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2604.21396","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.21396","pdf_url":"https://arxiv.org/pdf/2604.21396","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,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7160119641.pdf","grobid_xml":"https://content.openalex.org/works/W7160119641.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,84,170],"advancement":[1],"of":[2,36,50],"Large":[3],"Vision-Language":[4],"Models":[5],"(LVLMs)":[6],"requires":[7],"precise":[8],"local":[9],"region-based":[10],"reasoning":[11,41,69,103,128,162],"that":[12,124,156],"faithfully":[13],"grounds":[14],"the":[15,48,59,76,109],"model's":[16],"logic":[17],"in":[18,27],"actual":[19],"visual":[20,73,91],"evidence.":[21],"However,":[22],"existing":[23],"datasets":[24],"face":[25],"limitations":[26],"scalability":[28],"due":[29],"to":[30,71,180],"extensive":[31],"manual":[32],"annotation":[33],"and":[34,42,89,96,106,137,146,166,172],"lack":[35],"explicit":[37],"alignment":[38],"between":[39],"multi-step":[40],"corresponding":[43],"image":[44,77],"regions,":[45],"which":[46,65],"constrains":[47],"evaluation":[49,153],"model":[51],"trustworthiness.":[52],"To":[53],"address":[54],"these":[55],"challenges,":[56],"we":[57,119],"propose":[58],"Visual":[60],"Grounding":[61],"Chain-of-Thought":[62],"(VG-CoT)":[63],"dataset,":[64],"explicitly":[66],"links":[67],"each":[68],"step":[70],"real":[72],"evidence":[74,92],"within":[75],"through":[78,111],"a":[79,112,121],"fully":[80],"automated":[81],"three-stage":[82],"pipeline.":[83],"pipeline":[85],"first":[86],"extracts":[87],"object-":[88],"text-level":[90],"using":[93],"state-of-the-art":[94],"detection":[95,115],"OCR":[97],"models,":[98],"then":[99],"generates":[100],"step-by-step":[101],"grounded":[102],"with":[104,141],"GPT-4o,":[105],"finally":[107],"refines":[108],"grounding":[110],"rationale-driven":[113],"open-set":[114],"process.":[116],"In":[117],"addition,":[118],"introduce":[120],"new":[122],"benchmark":[123],"comprehensively":[125],"evaluates":[126],"LVLMs":[127],"across":[129],"three":[130],"complementary":[131],"dimensions:":[132],"Rationale":[133],"Quality,":[134],"Answer":[135],"Accuracy,":[136],"Reasoning-Answer":[138],"Alignment.":[139],"Experiments":[140],"representative":[142],"LVLMs,":[143],"including":[144],"LLaVA-1.5":[145],"Qwen2-VL,":[147],"demonstrate":[148],"consistent":[149],"improvements":[150],"on":[151],"most":[152],"metrics,":[154],"confirming":[155],"VG-CoT":[157],"effectively":[158],"enhances":[159],"trustworthy,":[160],"evidence-based":[161],"while":[163],"maintaining":[164],"scalable":[165],"cost-efficient":[167],"dataset":[168,171],"construction.":[169],"code":[173],"will":[174],"be":[175],"released":[176],"publicly":[177],"upon":[178],"acceptance":[179],"facilitate":[181],"further":[182],"research.":[183]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2026-05-05T00:00:00"}