{"id":"https://openalex.org/W4416034929","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.655","title":"MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs","display_name":"MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034929","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.655"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.655","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.655","pdf_url":"https://aclanthology.org/2025.findings-emnlp.655.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.655.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082096652","display_name":"Zaid Alyafeai","orcid":"https://orcid.org/0009-0003-1774-5236"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zaid Alyafeai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002926676","display_name":"Maged S. Al-shaibani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maged S. Al-shaibani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5024763828","display_name":"Bernard Ghanem","orcid":"https://orcid.org/0000-0002-5534-587X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bernard Ghanem","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":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12236","last_page":"12264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.2524000108242035,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.2524000108242035,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.15610000491142273,"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":0.04390000179409981,"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/metadata","display_name":"Metadata","score":0.7179999947547913},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.33090001344680786},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.3124000132083893},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.25760000944137573}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7179999947547913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6470000147819519},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4499000012874603},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43630000948905945},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4072999954223633},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2815999984741211},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2353000044822693}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.655","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.655","pdf_url":"https://aclanthology.org/2025.findings-emnlp.655.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.655","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.655","pdf_url":"https://aclanthology.org/2025.findings-emnlp.655.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":[{"id":"https://openalex.org/F4320322320","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034929.pdf","grobid_xml":"https://content.openalex.org/works/W4416034929.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Metadata":[0],"extraction":[1],"is":[2],"essential":[3],"for":[4,32,94,136,154],"cataloging":[5],"and":[6,13,89,117,144,151],"preserving":[7],"datasets,":[8],"enabling":[9],"effective":[10],"research":[11,105,156],"discovery":[12],"reproducibility,":[14],"especially":[15],"given":[16],"the":[17,30,104,134,148,155],"current":[18],"exponential":[19],"growth":[20],"in":[21,129],"scientific":[22,71],"research.While":[23],"Masader":[24],"(Alyafeai":[25],"et":[26],"al.,":[27],"2021b)":[28],"laid":[29],"groundwork":[31],"extracting":[33],"a":[34,57,99],"wide":[35],"range":[36],"of":[37,75,112],"metadata":[38,68],"attributes":[39,69],"from":[40,70],"Arabic":[41],"NLP":[42],"datasets'":[43],"scholarly":[44],"articles,":[45],"it":[46],"relies":[47],"heavily":[48],"on":[49,107],"manual":[50],"annotation.In":[51],"this":[52,108,131],"paper,":[53],"we":[54,97,121],"present":[55],"MOLE,":[56],"framework":[58],"that":[59,123],"leverages":[60],"Large":[61],"Language":[62],"Models":[63],"(LLMs)":[64],"to":[65,102,141],"automatically":[66],"extract":[67],"papers":[72],"covering":[73],"datasets":[74],"languages":[76],"other":[77],"than":[78],"Arabic.Our":[79],"schema-driven":[80],"methodology":[81],"processes":[82],"entire":[83],"documents":[84],"across":[85],"multiple":[86],"input":[87],"formats":[88],"incorporates":[90],"robust":[91],"validation":[92],"mechanisms":[93],"consistent":[95,143],"output.Additionally,":[96],"introduce":[98],"new":[100],"benchmark":[101],"evaluate":[103],"progress":[106],"task.Through":[109],"systematic":[110],"analysis":[111],"context":[113],"length,":[114],"few-shot":[115],"learning,":[116],"web":[118],"browsing":[119],"integration,":[120],"demonstrate":[122],"modern":[124],"LLMs":[125],"show":[126],"promising":[127],"results":[128],"automating":[130],"task,":[132],"highlighting":[133],"need":[135],"further":[137],"future":[138],"work":[139],"improvements":[140],"ensure":[142],"reliable":[145],"performance.We":[146],"release":[147],"code":[149],"1":[150],"dataset":[152],"2":[153],"community.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}