{"id":"https://openalex.org/W4412887783","doi":"https://doi.org/10.18653/v1/2025.findings-acl.957","title":"Can Multimodal Foundation Models Understand Schematic Diagrams? An Empirical Study on Information-Seeking QA over Scientific Papers","display_name":"Can Multimodal Foundation Models Understand Schematic Diagrams? An Empirical Study on Information-Seeking QA over Scientific Papers","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887783","doi":"https://doi.org/10.18653/v1/2025.findings-acl.957"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.957","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.957","pdf_url":"https://aclanthology.org/2025.findings-acl.957.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 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-acl.957.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037981788","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"]}]},{"author_position":"middle","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/A5108907561","display_name":"Chuhan Li","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":"Chuhan Li","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/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"]}]}],"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":1.673,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83305219,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"18598","last_page":"18631"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9897000193595886,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9897000193595886,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9887999892234802,"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/T10028","display_name":"Topic Modeling","score":0.9767000079154968,"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/schematic","display_name":"Schematic","score":0.9336283206939697},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.7315571904182434},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6938478350639343},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.4600429832935333},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.41408926248550415},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3599426746368408},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.3445832133293152},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.3424285054206848},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16539686918258667},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.09632265567779541}],"concepts":[{"id":"https://openalex.org/C192328126","wikidata":"https://www.wikidata.org/wiki/Q4514647","display_name":"Schematic","level":2,"score":0.9336283206939697},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.7315571904182434},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6938478350639343},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.4600429832935333},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41408926248550415},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3599426746368408},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3445832133293152},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3424285054206848},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16539686918258667},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.09632265567779541},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.957","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.957","pdf_url":"https://aclanthology.org/2025.findings-acl.957.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 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.957","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.957","pdf_url":"https://aclanthology.org/2025.findings-acl.957.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 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/W4412887783.pdf","grobid_xml":"https://content.openalex.org/works/W4412887783.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3154683910","https://openalex.org/W1846734616","https://openalex.org/W2359532622","https://openalex.org/W3134543635","https://openalex.org/W2921318524","https://openalex.org/W2377571686","https://openalex.org/W4380988671","https://openalex.org/W2130754836","https://openalex.org/W1925657225","https://openalex.org/W4386651600"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"MISS-QA,":[3],"the":[4,11,50,54,57,96],"first":[5],"benchmark":[6],"specifically":[7],"designed":[8],"to":[9,15,106],"evaluate":[10],"ability":[12],"of":[13,53,59,83,100],"models":[14,32,76,108],"interpret":[16],"schematic":[17,37],"diagrams":[18,38],"within":[19],"scientific":[20,28,112],"literature.MISS-QA":[21],"comprises":[22],"1,500":[23],"expert-annotated":[24],"examples":[25],"over":[26],"465":[27],"papers.In":[29],"this":[30],"benchmark,":[31],"are":[33],"tasked":[34],"with":[35],"interpreting":[36],"that":[39],"illustrate":[40],"research":[41],"overviews":[42],"and":[43,77,89,98],"answering":[44],"corresponding":[45],"information-seeking":[46],"questions":[47,88],"based":[48],"on":[49,80,86],"broader":[51],"context":[52],"paper.We":[55],"assess":[56],"performance":[58,72,85],"18":[60],"frontier":[61],"multimodal":[62,111],"foundation":[63],"models,":[64,102],"including":[65],"o4mini,":[66],"Gemini-2.5-Flash,and":[67],"Qwen2.5-VL.We":[68],"reveal":[69],"a":[70],"significant":[71],"gap":[73],"between":[74],"these":[75],"human":[78],"experts":[79],"MISS-QA.Our":[81],"analysis":[82,93],"model":[84],"unanswerable":[87],"our":[90],"detailed":[91],"error":[92],"further":[94],"highlight":[95],"strengths":[97],"limitations":[99],"current":[101],"offering":[103],"key":[104],"insights":[105],"enhance":[107],"in":[109],"comprehending":[110],"literature.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}