{"id":"https://openalex.org/W4416034249","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1257","title":"Looking Beyond the Pixels: Evaluating Visual Metaphor Understanding in VLMs","display_name":"Looking Beyond the Pixels: Evaluating Visual Metaphor Understanding in VLMs","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034249","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1257"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1257","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1257","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1257.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1257.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033181114","display_name":"Malay K. Kundu","orcid":"https://orcid.org/0000-0002-9010-9100"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manishit Kundu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007774416","display_name":"Sumit Shekhar","orcid":"https://orcid.org/0000-0002-5683-2290"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sumit Shekhar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5065100828","display_name":"Pushpak Bhattacharyya","orcid":"https://orcid.org/0000-0001-5319-5508"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pushpak Bhattacharyya","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":0.2936407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23137","last_page":"23158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.6161999702453613,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.6161999702453613,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.06390000134706497,"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.05719999969005585,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metaphor","display_name":"Metaphor","score":0.5884000062942505},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.36390000581741333},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3102000057697296},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3027999997138977},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.28780001401901245},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.28760001063346863}],"concepts":[{"id":"https://openalex.org/C2778311575","wikidata":"https://www.wikidata.org/wiki/Q18534","display_name":"Metaphor","level":2,"score":0.5884000062942505},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.39820000529289246},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3813999891281128},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.33660000562667847},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.33390000462532043},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3222000002861023},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.2890999913215637},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.2750000059604645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2750000059604645},{"id":"https://openalex.org/C2776402256","wikidata":"https://www.wikidata.org/wiki/Q2633818","display_name":"Conceptual metaphor","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2615000009536743},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1257","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1257","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1257.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1257","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1257","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1257.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034249.pdf","grobid_xml":"https://content.openalex.org/works/W4416034249.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visual":[0,56,61],"metaphors":[1],"are":[2],"a":[3,17,21,38,91],"complex":[4],"vision-language":[5],"phenomenon":[6],"that":[7,96,108,127,141],"requires":[8],"both":[9],"perceptual":[10],"and":[11,28,34,45,60,83],"conceptual":[12],"reasoning":[13],"to":[14,24],"understand.They":[15],"provide":[16],"valuable":[18],"test":[19],"of":[20,174,179],"model's":[22],"ability":[23],"interpret":[25],"visual":[26,39,124,176],"input":[27],"reason":[29],"about":[30],"it":[31],"with":[32,160],"creativity":[33],"coherence.We":[35],"introduce":[36,90],"ImageMet,":[37,71],"metaphor":[40,148,177],"dataset,":[41],"featuring":[42],"2177":[43],"synthetic":[44],"350":[46],"human-annotated":[47],"images.We":[48],"benchmark":[49],"several":[50],"SOTA":[51],"VLMs":[52,116],"on":[53,70,87,112,132],"two":[54],"tasks:":[55],"Metaphor":[57,62],"Captioning":[58],"(VMC)":[59],"VQA":[63],"(VM-VQA).We":[64],"establish":[65],"strong":[66,110],"baselines":[67,100],"by":[68],"fine-tuning":[69],"which":[72],"yields":[73],"substantial":[74],"performance":[75,111],"gains":[76],"in":[77,102,105,122,147],"VMC":[78,114],"(+4.67%SBERT-Similarity,":[79],"+4.84%":[80],"task-specific":[81,92],"metric)":[82],"VM-VQA":[84],"(+9.3%":[85],"Accuracy":[86],"average).Additionally,":[88],"we":[89],"CoT":[93],"prompting":[94],"strategy":[95],"outperforms":[97],"standard":[98],"few-shot":[99],"(+1.99%":[101],"VMC,":[103],"+5.21%":[104],"VM-VQA).We":[106],"observe":[107],"despite":[109],"the":[113,152,168,175,180],"task,":[115],"still":[117],"significantly":[118],"lag":[119],"behind":[120],"humans":[121],"understanding":[123,178],"metaphors,":[125],"indicating":[126],"their":[128],"success":[129],"often":[130,145],"relies":[131],"learned":[133],"associations":[134],"rather":[135],"than":[136],"genuine":[137],"analytical":[138],"reasoning.We":[139],"note":[140],"this":[142],"gap":[143],"is":[144],"obscured":[146],"captioning":[149],"tasks":[150],"where":[151],"automatic":[153],"metrics":[154],"correlate":[155],"only":[156],"moderately":[157],"at":[158],"best":[159],"human":[161],"judgment":[162],"(Pearson":[163],"r":[164],"<":[165],"0.6),":[166],"highlighting":[167],"need":[169],"for":[170],"careful,":[171],"holistic":[172],"evaluation":[173],"models.":[181]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}