{"id":"https://openalex.org/W4417252860","doi":"https://doi.org/10.1109/iccv51701.2025.01886","title":"ARGUS: Hallucination and Omission Evaluation in Video-LLMs","display_name":"ARGUS: Hallucination and Omission Evaluation in Video-LLMs","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417252860","doi":"https://doi.org/10.1109/iccv51701.2025.01886"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01886","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.07371","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030601126","display_name":"Ruchit Rawal","orcid":"https://orcid.org/0000-0003-1794-9573"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruchit Rawal","raw_affiliation_strings":["University of Maryland,College Park,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027099536","display_name":"Reza Shirkavand","orcid":"https://orcid.org/0000-0003-1455-7419"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reza Shirkavand","raw_affiliation_strings":["University of Maryland,College Park,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109199932","display_name":"Heng Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heng Huang","raw_affiliation_strings":["University of Maryland,College Park,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078715414","display_name":"Gowthami Somepalli","orcid":"https://orcid.org/0000-0002-5380-1413"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gowthami Somepalli","raw_affiliation_strings":["University of Maryland,College Park,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060687985","display_name":"Tom Goldstein","orcid":"https://orcid.org/0000-0003-1660-9307"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tom Goldstein","raw_affiliation_strings":["University of Maryland,College Park,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35553713,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20280","last_page":"20290"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8946999907493591,"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":0.8946999907493591,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.012000000104308128,"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":0.009399999864399433,"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/hallucinating","display_name":"Hallucinating","score":0.9018999934196472},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8949999809265137},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.6481000185012817},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5853999853134155},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5347999930381775},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4431999921798706},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.38420000672340393}],"concepts":[{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.9018999934196472},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8949999809265137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7459999918937683},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.6481000185012817},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5853999853134155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5794000029563904},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5347999930381775},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5055999755859375},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3433000147342682},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.337799996137619},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C2776760603","wikidata":"https://www.wikidata.org/wiki/Q3622471","display_name":"Argus","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01886","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:2506.07371","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.07371","pdf_url":"https://arxiv.org/pdf/2506.07371","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2506.07371","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.07371","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.07371","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.07371","pdf_url":"https://arxiv.org/pdf/2506.07371","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1629228142","display_name":null,"funder_award_id":"2347617","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"},{"id":"https://openalex.org/G4945365176","display_name":null,"funder_award_id":"s2405416","funder_id":"https://openalex.org/F4320337398","funder_display_name":"Division of Biological Infrastructure"},{"id":"https://openalex.org/G91153074","display_name":null,"funder_award_id":"2348306","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"}],"funders":[{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"},{"id":"https://openalex.org/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"},{"id":"https://openalex.org/F4320337398","display_name":"Division of Biological Infrastructure","ror":"https://ror.org/04qn9mx93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0],"large":[1],"language":[2],"models":[3],"have":[4],"not":[5],"yet":[6],"been":[7],"widely":[8],"deployed,":[9],"largely":[10],"due":[11],"to":[12,15,68],"their":[13],"tendency":[14],"hallucinate.":[16],"Typical":[17],"benchmarks":[18],"for":[19],"Video-LLMs":[20],"rely":[21],"simply":[22],"on":[23,32,43],"multiple-choice":[24],"questions.":[25],"Unfortunately,":[26],"VideoLLMs":[27],"hallucinate":[28],"far":[29],"more":[30],"aggressively":[31],"freeform":[33,60],"text":[34],"generation":[35],"tasks":[36],"like":[37],"video":[38,61,91,118],"captioning":[39,62,119],"than":[40],"they":[41],"do":[42],"multiple":[44],"choice":[45],"verification":[46],"tasks.":[47],"To":[48],"address":[49],"this":[50],"weakness,":[51],"we":[52,78,97],"propose":[53],"ARGUS,":[54],"a":[55,114],"VideoLLM":[56,66],"benchmark":[57],"that":[58],"measures":[59],"performance.":[63,120],"By":[64],"comparing":[65],"outputs":[67],"human":[69],"ground":[70],"truth":[71],"captions,":[72],"ARGUS":[73],"quantifies":[74],"dual":[75,111],"metrics.":[76],"First,":[77],"measure":[79,98],"the":[80,85,99,103],"rate":[81,100],"of":[82,87,117],"hallucinations":[83],"in":[84],"form":[86,113],"incorrect":[88],"statements":[89],"about":[90],"content":[92],"or":[93],"temporal":[94],"relationships.":[95],"Second,":[96],"at":[101],"which":[102],"model":[104],"omits":[105],"important":[106],"descriptive":[107],"details.":[108],"Together,":[109],"these":[110],"metrics":[112],"comprehensive":[115],"view":[116]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}