{"id":"https://openalex.org/W7162078936","doi":"https://doi.org/10.48550/arxiv.2605.21728","title":"BEiTScore: Reference-free Image Captioning Evaluation with an Efficient Cross-Encoder Model","display_name":"BEiTScore: Reference-free Image Captioning Evaluation with an Efficient Cross-Encoder Model","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W7162078936","doi":"https://doi.org/10.48550/arxiv.2605.21728"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.21728","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21728","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.21728","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136790122","display_name":"Gon\u00e7alo Gomes","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gomes, Gon\u00e7alo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136792311","display_name":"Bruno Martins","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martins, Bruno","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5004372721","display_name":"Chrysoula Zerva","orcid":"https://orcid.org/0000-0002-4031-9492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zerva, Chrysoula","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9957000017166138,"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":0.9957000017166138,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.00039999998989515007,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0003000000142492354,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9136999845504761},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7056999802589417},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6607000231742859},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6208000183105469},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5867000222206116},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.49900001287460327},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.46070000529289246},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.44359999895095825}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9136999845504761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986999750137329},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7056999802589417},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6607000231742859},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6208000183105469},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5867000222206116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5716000199317932},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5012000203132629},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.49900001287460327},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.46070000529289246},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.44359999895095825},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39430001378059387},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.36399999260902405},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3125},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28600001335144043},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.21728","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21728","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.21728","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21728","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5110079646110535,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Image":[0],"captioning":[1,137],"evaluation":[2,23,138],"remains":[3],"a":[4,71,82,89,95,106,130],"significant":[5],"challenge,":[6],"as":[7,16,38,51,67],"vision-language":[8],"models":[9],"evolve":[10],"toward":[11],"more":[12],"challenging":[13],"capabilities":[14],"such":[15,50],"generating":[17],"long-form":[18],"and":[19],"context-rich":[20],"descriptions.":[21],"State-of-the-art":[22],"metrics":[24],"involve":[25],"extensive":[26],"computational":[27,100],"costs":[28],"associated":[29],"with":[30,99],"the":[31,44,77,146,154],"use":[32],"of":[33,46,56,61],"Large":[34],"Language":[35],"Models":[36],"(LLMs)":[37],"judges,":[39],"or":[40,59,162],"instead":[41],"suffer":[42],"from":[43,88],"limitations":[45],"standard":[47],"CLIP-based":[48],"encoders,":[49],"strict":[52],"token":[53],"limits,":[54],"lack":[55,60],"fine-grained":[57,124],"sensitivity,":[58],"compositional":[62],"generalization":[63],"by":[64],"treating":[65],"captions":[66],"``bags-of-words.''":[68],"We":[69,127],"propose":[70],"new":[72,131],"learned":[73],"metric":[74,148],"that":[75,85,145],"tackles":[76],"aforementioned":[78],"challenges,":[79],"based":[80],"on":[81],"lightweight":[83],"cross-encoder":[84],"is":[86],"initialized":[87],"visual":[90],"question-answering":[91],"model":[92,121],"checkpoint,":[93],"balancing":[94],"strong":[96],"weight":[97],"initialization":[98],"efficiency.":[101],"Our":[102],"training":[103],"scheme":[104],"uses":[105],"carefully":[107],"assembled":[108],"data":[109,117],"mixture":[110],"for":[111,157],"supervised":[112],"learning,":[113],"featuring":[114],"adversarial":[115],"LLM-based":[116],"augmentations":[118],"to":[119,123,134],"enhance":[120],"sensitivity":[122],"visual-linguistic":[125],"errors.":[126],"also":[128],"introduce":[129],"benchmark":[132],"designed":[133],"assess":[135],"detailed":[136],"across":[139],"diverse":[140],"scenarios.":[141],"Experimental":[142],"results":[143],"demonstrate":[144],"proposed":[147],"achieves":[149],"state-of-the-art":[150],"performance":[151],"while":[152],"maintaining":[153],"efficiency":[155],"required":[156],"large-scale":[158],"benchmarking,":[159],"quality-aware":[160],"decoding,":[161],"reward":[163],"guidance.":[164]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-23T00:00:00"}