{"id":"https://openalex.org/W4412945493","doi":"https://doi.org/10.18653/v1/2025.acl-long.420","title":"SciVer: Evaluating Foundation Models for Multimodal Scientific Claim Verification","display_name":"SciVer: Evaluating Foundation Models for Multimodal Scientific Claim Verification","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945493","doi":"https://doi.org/10.18653/v1/2025.acl-long.420"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.420","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.420","pdf_url":"https://aclanthology.org/2025.acl-long.420.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.420.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045077119","display_name":"Chengye Wang","orcid":"https://orcid.org/0000-0002-6184-9863"},"institutions":[{"id":"https://openalex.org/I4210145818","display_name":"Yale-NUS College","ror":null,"country_code":"SG","type":null,"lineage":["https://openalex.org/I4210145818"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chengye Wang","raw_affiliation_strings":["Yale NLP Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale NLP Lab","institution_ids":["https://openalex.org/I4210145818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114889635","display_name":"Yifei Shen","orcid":"https://orcid.org/0000-0001-7174-4793"},"institutions":[{"id":"https://openalex.org/I4210145818","display_name":"Yale-NUS College","ror":null,"country_code":"SG","type":null,"lineage":["https://openalex.org/I4210145818"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yifei Shen","raw_affiliation_strings":["Yale NLP Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale NLP Lab","institution_ids":["https://openalex.org/I4210145818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119204535","display_name":"Zexi Kuang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145818","display_name":"Yale-NUS College","ror":null,"country_code":"SG","type":null,"lineage":["https://openalex.org/I4210145818"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zexi Kuang","raw_affiliation_strings":["Yale NLP Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale NLP Lab","institution_ids":["https://openalex.org/I4210145818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064858748","display_name":"Arman Cohan","orcid":"https://orcid.org/0000-0002-8954-2724"},"institutions":[{"id":"https://openalex.org/I4210145818","display_name":"Yale-NUS College","ror":null,"country_code":"SG","type":null,"lineage":["https://openalex.org/I4210145818"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Arman Cohan","raw_affiliation_strings":["Yale NLP Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale NLP Lab","institution_ids":["https://openalex.org/I4210145818"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101240019","display_name":"Yilun Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145818","display_name":"Yale-NUS College","ror":null,"country_code":"SG","type":null,"lineage":["https://openalex.org/I4210145818"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yilun Zhao","raw_affiliation_strings":["Yale NLP Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale NLP Lab","institution_ids":["https://openalex.org/I4210145818"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210145818"],"apc_list":null,"apc_paid":null,"fwci":3.346,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92477414,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8562","last_page":"8579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9398999810218811,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9398999810218811,"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/foundation","display_name":"Foundation (evidence)","score":0.8161298036575317},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6501558423042297},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.333122193813324},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.04547417163848877}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.8161298036575317},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6501558423042297},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.333122193813324},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.04547417163848877},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.420","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.420","pdf_url":"https://aclanthology.org/2025.acl-long.420.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"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.420","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.420","pdf_url":"https://aclanthology.org/2025.acl-long.420.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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945493.pdf","grobid_xml":"https://content.openalex.org/works/W4412945493.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2358060160","https://openalex.org/W2035483685"],"abstract_inverted_index":{"We":[0],"introduce":[1],"SCIVER,":[2],"the":[3,10,56],"first":[4],"benchmark":[5],"specifically":[6],"designed":[7],"to":[8,15,105],"evaluate":[9],"ability":[11],"of":[12,24,58,86],"foundation":[13,62],"models":[14,77],"verify":[16],"claims":[17],"within":[18],"a":[19,37,71],"multimodal":[20,42,61,112],"scientific":[21,30,43,113],"context.SCIVER":[22],"consists":[23],"3,000":[25],"expert-annotated":[26,52],"examples":[27],"over":[28],"1,113":[29],"papers,":[31],"covering":[32],"four":[33],"subsets,":[34],"each":[35,49],"representing":[36],"common":[38],"reasoning":[39,110],"type":[40],"in":[41,98,111],"claim":[44],"verification.To":[45],"enable":[46],"fine-grained":[47],"evaluation,":[48],"example":[50],"includes":[51],"supporting":[53],"evidence.We":[54],"assess":[55],"performance":[57,73],"21":[59],"state-of-the-art":[60],"models,":[63,101],"including":[64],"o4mini,":[65],"Gemini-2.5-Flash,Llama-3.2-Vision,":[66],"and":[67,78,90,109],"Qwen2.5-VL.Our":[68],"experiment":[69],"reveals":[70],"substantial":[72],"gap":[74],"between":[75],"these":[76],"human":[79],"experts":[80],"on":[81],"SCIVER.Through":[82],"an":[83],"in-depth":[84],"analysis":[85],"retrieval-augmented":[87],"generation":[88],"(RAG),":[89],"human-conducted":[91],"error":[92],"evaluations,":[93],"we":[94],"identify":[95],"critical":[96],"limitations":[97],"current":[99],"open-source":[100],"offering":[102],"key":[103],"insights":[104],"advance":[106],"models'":[107],"comprehension":[108],"literature":[114],"tasks.":[115]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}