{"id":"https://openalex.org/W4412945593","doi":"https://doi.org/10.18653/v1/2025.acl-long.372","title":"VLM2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues","display_name":"VLM2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945593","doi":"https://doi.org/10.18653/v1/2025.acl-long.372"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.372","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.372","pdf_url":"https://aclanthology.org/2025.acl-long.372.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.372.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056583700","display_name":"Jianshu Zhang","orcid":"https://orcid.org/0000-0001-6536-2633"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianshu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102613789","display_name":"Dongyu Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongyu Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028182071","display_name":"Renjie Pi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Renjie Pi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086233510","display_name":"Paul Pu Liang","orcid":"https://orcid.org/0000-0001-7768-3610"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul Pu Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5029408111","display_name":"Yi R. Fung","orcid":"https://orcid.org/0009-0006-1869-0363"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi R. Fung","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":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25507307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7510","last_page":"7545"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11438","display_name":"Retinal Imaging and Analysis","score":0.33980000019073486,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11438","display_name":"Retinal Imaging and Analysis","score":0.33980000019073486,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/link","display_name":"Link (geometry)","score":0.8165555000305176},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6643457412719727},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6352330446243286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41845715045928955},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1597389578819275},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07916468381881714}],"concepts":[{"id":"https://openalex.org/C2778753846","wikidata":"https://www.wikidata.org/wiki/Q6554239","display_name":"Link (geometry)","level":2,"score":0.8165555000305176},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6643457412719727},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6352330446243286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41845715045928955},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1597389578819275},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07916468381881714},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.372","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.372","pdf_url":"https://aclanthology.org/2025.acl-long.372.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-168491","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-168491","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.372","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.372","pdf_url":"https://aclanthology.org/2025.acl-long.372.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945593.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1518185400","https://openalex.org/W3200586296","https://openalex.org/W2390279801","https://openalex.org/W4230332972","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W1998033311"],"abstract_inverted_index":{"Visually":[0,66],"linking":[1],"matching":[2],"cues":[3],"is":[4],"a":[5,58,96,114],"crucial":[6],"ability":[7,108,163],"in":[8,17,106,147],"daily":[9],"life,":[10],"such":[11],"as":[12],"identifying":[13],"the":[14,31],"same":[15],"person":[16],"multiple":[18],"photos":[19],"based":[20],"on":[21,119,136],"their":[22],"cues,":[23,69,112],"even":[24],"without":[25],"knowing":[26],"who":[27],"they":[28,44],"are.":[29],"Despite":[30],"extensive":[32],"knowledge":[33],"that":[34],"vision-language":[35],"models":[36],"(VLMs)":[37],"possess,":[38],"it":[39],"remains":[40],"largely":[41],"unexplored":[42],"whether":[43,63],"are":[45],"capable":[46],"of":[47,87,98],"performing":[48],"this":[49],"fundamental":[50],"task.":[51],"To":[52],"address":[53],"this,":[54],"we":[55,122],"introduce":[56],"VLM2-Bench,":[57],"benchmark":[59],"designed":[60],"to":[61,95,109,130,150,164],"assess":[62],"VLMs":[64],"can":[65],"Link":[67],"Matching":[68],"with":[70,84],"9":[71],"subtasks":[72],"and":[73,90,133,154,167],"over":[74],"3,000":[75],"test":[76],"cases.":[77],"Comprehensive":[78],"evaluation":[79],"across":[80],"twelve":[81],"VLMs,":[82],"along":[83],"further":[85],"analysis":[86],"various":[88],"language-side":[89],"vision-side":[91],"prompting":[92],"methods,":[93],"leads":[94],"total":[97],"eight":[99],"key":[100],"findings.":[101],"We":[102],"identify":[103],"critical":[104],"challenges":[105],"models\u2019":[107,162],"link":[110],"visual":[111,128,171],"highlighting":[113],"significant":[115],"performance":[116],"gap.":[117],"Based":[118],"these":[120],"insights,":[121],"advocate":[123],"for":[124,143],"(i)":[125],"enhancing":[126],"core":[127],"capabilities":[129],"improve":[131],"adaptability":[132],"reduce":[134],"reliance":[135],"prior":[137],"knowledge,":[138],"(ii)":[139],"establishing":[140],"clearer":[141],"principles":[142],"integrating":[144],"language-based":[145],"reasoning":[146],"vision-centric":[148],"tasks":[149],"prevent":[151],"unnecessary":[152],"biases,":[153],"(iii)":[155],"shifting":[156],"vision-text":[157],"training":[158],"paradigms":[159],"toward":[160],"fostering":[161],"independently":[165],"structure":[166],"infer":[168],"relationships":[169],"among":[170],"cues.<br/>":[172]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
