{"id":"https://openalex.org/W7166813714","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2122","title":"CaRVE: Critiquing and Refining Visual Elaborations for Figurative Language Illustrations","display_name":"CaRVE: Critiquing and Refining Visual Elaborations for Figurative Language Illustrations","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166813714","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2122"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.2122","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2122","pdf_url":"https://aclanthology.org/2026.findings-acl.2122.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: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.2122.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139735514","display_name":"Manishit Kundu","orcid":null},"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/A5120092105","display_name":"Tejomay Kishor Padole","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tejomay Kishor Padole","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139743532","display_name":"Sumit Shekhar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sumit Shekhar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139812780","display_name":"Biplab Banerjee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Biplab Banerjee","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":0.83301297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"42760","last_page":"42777"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10789","display_name":"Interactive and Immersive Displays","score":0.18940000236034393,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10789","display_name":"Interactive and Immersive Displays","score":0.18940000236034393,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10799","display_name":"Data Visualization and Analytics","score":0.17630000412464142,"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/T10470","display_name":"Usability and User Interface Design","score":0.05339999869465828,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/literal-and-figurative-language","display_name":"Literal and figurative language","score":0.7429999709129333},{"id":"https://openalex.org/keywords/refining","display_name":"Refining (metallurgy)","score":0.6259999871253967},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.4163999855518341},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3093999922275543},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.30390000343322754}],"concepts":[{"id":"https://openalex.org/C46182478","wikidata":"https://www.wikidata.org/wiki/Q7363315","display_name":"Literal and figurative language","level":2,"score":0.7429999709129333},{"id":"https://openalex.org/C60044698","wikidata":"https://www.wikidata.org/wiki/Q1283324","display_name":"Refining (metallurgy)","level":2,"score":0.6259999871253967},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5527999997138977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4496000111103058},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3668999969959259},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31189998984336853},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C119657128","wikidata":"https://www.wikidata.org/wiki/Q11633","display_name":"Photography","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26919999718666077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.2122","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2122","pdf_url":"https://aclanthology.org/2026.findings-acl.2122.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: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.2122","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2122","pdf_url":"https://aclanthology.org/2026.findings-acl.2122.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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5423319339752197,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166813714.pdf","grobid_xml":"https://content.openalex.org/works/W7166813714.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Illustrating":[0],"figurative":[1,44,69,100,148],"language":[2,113],"remains":[3],"challenging":[4],"due":[5],"to":[6,22,39,67,154],"its":[7],"non-literal":[8],"semantics,":[9],"and":[10,30,59,64,86,115],"existing":[11],"text-to-image":[12,149],"frameworks":[13],"rely":[14],"heavily":[15],"on":[16,82],"proprietary":[17],"models":[18,55,114,130],"or":[19],"human":[20,93],"supervision":[21],"achieve":[23],"adequate":[24],"alignment.We":[25],"introduce":[26,139],"CaRVE,":[27],"a":[28,76,87,132,144],"lightweight":[29],"fully":[31],"open-source":[32,72,117],"critique-driven":[33],"framework":[34,146],"that":[35,120],"employs":[36,151],"VLM":[37],"feedback":[38,134],"refine":[40,156],"visual":[41,58,157],"elaborations":[42,158],"for":[43,147,159],"image":[45,101,160],"generation.CaRVE":[46,150],"bridges":[47],"the":[48],"semantic":[49,122,165],"alignment":[50,166],"gap":[51,123],"even":[52,167],"in":[53,92,128],"sub-4B":[54,170],"by":[56,104],"correcting":[57],"conceptual":[60],"misalignments,":[61],"reducing":[62],"over-literalization,":[63],"improving":[65],"robustness":[66],"complex":[68],"expressions.Using":[70],"only":[71],"models,":[73],"CaRVE":[74,108],"achieves":[75],"6.49%":[77],"improvement":[78],"over":[79],"prior":[80],"baselines":[81],"intrinsic":[83],"automatic":[84],"evaluations":[85],"+0.37":[88],"average":[89],"rank":[90],"gain":[91],"preference.We":[94],"further":[95],"release":[96],"MetaCaRVE,":[97],"an":[98],"enhanced":[99],"dataset":[102],"constructed":[103],"refining":[105],"HAIVMet":[106],"using":[107],"1":[109],".1":[110],"https://github.com/manishitkundu/CaRVE_ACL_":[111],"2026":[112],"smaller,":[116],"LLMs.We":[118],"posit":[119],"this":[121,136],"can":[124],"be":[125],"effectively":[126],"bridged":[127],"smaller":[129,169],"through":[131],"VLM-critiquedriven":[133],"mechanism.In":[135],"work,":[137],"we":[138],"Critiquing-and-Refining":[140],"Visual":[141],"Elaborations":[142],"(CaRVE),":[143],"VLM-feedback-driven":[145],"VLM-based":[152],"critique":[153],"iteratively":[155],"generation,":[161],"yielding":[162],"significantly":[163],"improved":[164],"with":[168],"models.":[171]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
