{"id":"https://openalex.org/W7151211911","doi":"https://doi.org/10.1109/icmla66185.2025.00124","title":"Towards Reliable Reasoning in Vision-Language Models","display_name":"Towards Reliable Reasoning in Vision-Language Models","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7151211911","doi":"https://doi.org/10.1109/icmla66185.2025.00124"},"language":null,"primary_location":{"id":"doi:10.1109/icmla66185.2025.00124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133117338","display_name":"Chinh Hoang","orcid":null},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]},{"id":"https://openalex.org/I151440000","display_name":"Lincoln Electric (United States)","ror":"https://ror.org/04y2bnd24","country_code":"US","type":"company","lineage":["https://openalex.org/I151440000"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chinh Hoang","raw_affiliation_strings":["University of Nebraska-Lincoln,Electrical and Computer Engineering,Lincoln,NE,USA"],"affiliations":[{"raw_affiliation_string":"University of Nebraska-Lincoln,Electrical and Computer Engineering,Lincoln,NE,USA","institution_ids":["https://openalex.org/I114395901","https://openalex.org/I151440000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053830039","display_name":"Youssef Nassef","orcid":null},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]},{"id":"https://openalex.org/I151440000","display_name":"Lincoln Electric (United States)","ror":"https://ror.org/04y2bnd24","country_code":"US","type":"company","lineage":["https://openalex.org/I151440000"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Youssef Nassef","raw_affiliation_strings":["University of Nebraska-Lincoln,Electrical and Computer Engineering,Lincoln,NE,USA"],"affiliations":[{"raw_affiliation_string":"University of Nebraska-Lincoln,Electrical and Computer Engineering,Lincoln,NE,USA","institution_ids":["https://openalex.org/I114395901","https://openalex.org/I151440000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101971620","display_name":"Mohammad Rashedul Hasan","orcid":"https://orcid.org/0000-0002-9818-9600"},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]},{"id":"https://openalex.org/I151440000","display_name":"Lincoln Electric (United States)","ror":"https://ror.org/04y2bnd24","country_code":"US","type":"company","lineage":["https://openalex.org/I151440000"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Rashedul Hasan","raw_affiliation_strings":["University of Nebraska-Lincoln,Electrical and Computer Engineering,Lincoln,NE,USA"],"affiliations":[{"raw_affiliation_string":"University of Nebraska-Lincoln,Electrical and Computer Engineering,Lincoln,NE,USA","institution_ids":["https://openalex.org/I114395901","https://openalex.org/I151440000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5133117338"],"corresponding_institution_ids":["https://openalex.org/I114395901","https://openalex.org/I151440000"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74886586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"842","last_page":"847"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3605000078678131,"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":0.3605000078678131,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.19050000607967377,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.061500001698732376,"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/set","display_name":"Set (abstract data type)","score":0.25130000710487366},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.25060001015663147},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.24220000207424164},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.24070000648498535},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.23309999704360962}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.572700023651123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4410000145435333},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25130000710487366},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25060001015663147},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.24220000207424164},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24070000648498535},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.23309999704360962},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2290000021457672},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22840000689029694},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2249000072479248}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmla66185.2025.00124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2101234009","https://openalex.org/W2950866572","https://openalex.org/W2970476646","https://openalex.org/W3102659883","https://openalex.org/W3134354193","https://openalex.org/W4312956471","https://openalex.org/W4389523832","https://openalex.org/W4392935324","https://openalex.org/W4393160204","https://openalex.org/W4402670859","https://openalex.org/W4402753774","https://openalex.org/W4402754009","https://openalex.org/W4404544903","https://openalex.org/W4405595839","https://openalex.org/W7133220561","https://openalex.org/W7133227958"],"related_works":[],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"(VLMs)":[2],"excel":[3],"in":[4,57,104,133],"image":[5],"understanding":[6,124],"but":[7],"often":[8],"hallucinate,":[9],"generating":[10],"descriptions":[11],"of":[12,96,113,125],"non-existent":[13],"objects.":[14],"While":[15,98],"prior":[16],"work":[17,121],"has":[18],"addressed":[19],"static":[20],"object":[21,31,39],"hallucination,":[22],"we":[23,64],"identify":[24],"a":[25,66],"distinct,":[26],"understudied":[27],"failure":[28,127],"mode:":[29],"hypothetical":[30],"hallucination":[32],"(HOH),":[33],"where":[34],"VLMs":[35,77,85],"misjudge":[36],"whether":[37],"an":[38],"could":[40],"plausibly":[41],"appear":[42],"under":[43],"altered":[44],"temporal":[45],"or":[46],"contextual":[47,73],"conditions.":[48],"This":[49],"phenomenon,":[50],"related":[51],"to":[52,75,90],"counterfactual":[53],"reasoning,":[54],"exposes":[55],"gaps":[56],"dynamic":[58],"multimodal":[59,136],"reasoning.":[60,80,137],"To":[61],"mitigate":[62],"HOH,":[63],"propose":[65],"training-free,":[67],"prompt-based":[68,114],"meta-reasoning":[69],"approach":[70],"that":[71],"leverages":[72],"cues":[74],"guide":[76],"toward":[78],"deliberate":[79],"Evaluations":[81],"across":[82],"12":[83],"diverse":[84],"reveal":[86],"variable":[87,108],"performance,":[88],"sensitivity":[89],"query":[91],"phrasing,":[92],"and":[93,129],"inconsistent":[94],"effectiveness":[95],"meta-information.":[97],"our":[99,120],"method":[100],"enhances":[101],"reasoning":[102],"accuracy":[103],"several":[105],"models,":[106],"its":[107],"impact":[109],"underscores":[110],"the":[111,123,131],"fragility":[112],"interventions.":[115],"By":[116],"exposing":[117],"these":[118],"complexities,":[119],"deepens":[122],"VLM":[126],"modes":[128],"emphasizes":[130],"challenges":[132],"achieving":[134],"robust":[135]},"counts_by_year":[],"updated_date":"2026-04-09T06:08:40.794217","created_date":"2026-04-08T00:00:00"}