{"id":"https://openalex.org/W7126444615","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.26","title":"Large Language Models for Scientific Information Extraction: An Empirical Study for Virology","display_name":"Large Language Models for Scientific Information Extraction: An Empirical Study for Virology","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126444615","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.26"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.26","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.26","pdf_url":"https://aclanthology.org/2024.findings-eacl.26.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: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.26.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093751352","display_name":"Mahsa Shamsabadi","orcid":"https://orcid.org/0009-0009-4062-7223"},"institutions":[{"id":"https://openalex.org/I2802635041","display_name":"Technische Informationsbibliothek (TIB)","ror":"https://ror.org/04aj4c181","country_code":"DE","type":"archive","lineage":["https://openalex.org/I2802635041","https://openalex.org/I315704651"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mahsa Shamsabadi","raw_affiliation_strings":["TIB Leibniz Information Centre for Science and Technology , Hannover , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TIB Leibniz Information Centre for Science and Technology , Hannover , Germany","institution_ids":["https://openalex.org/I2802635041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108315986","display_name":"Jennifer D\u2019Souza","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jennifer D\u2019Souza","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124629920","display_name":"S\u00f6ren Auer","orcid":null},"institutions":[{"id":"https://openalex.org/I2802635041","display_name":"Technische Informationsbibliothek (TIB)","ror":"https://ror.org/04aj4c181","country_code":"DE","type":"archive","lineage":["https://openalex.org/I2802635041","https://openalex.org/I315704651"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"S\u00f6ren Auer","raw_affiliation_strings":["TIB Leibniz Information Centre for Science and Technology , Hannover , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TIB Leibniz Information Centre for Science and Technology , Hannover , Germany","institution_ids":["https://openalex.org/I2802635041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2021,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8393288,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"374","last_page":"392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.24330000579357147,"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":0.24330000579357147,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.10180000215768814,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.09049999713897705,"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/empirical-research","display_name":"Empirical research","score":0.5963000059127808},{"id":"https://openalex.org/keywords/empirical-modelling","display_name":"Empirical modelling","score":0.35109999775886536},{"id":"https://openalex.org/keywords/information-system","display_name":"Information system","score":0.3086000084877014},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2930000126361847}],"concepts":[{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.5963000059127808},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5841000080108643},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4311000108718872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.414900004863739},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37439998984336853},{"id":"https://openalex.org/C133199616","wikidata":"https://www.wikidata.org/wiki/Q25386885","display_name":"Empirical modelling","level":2,"score":0.35109999775886536},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3375000059604645},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2728999853134155},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2669999897480011},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.26","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.26","pdf_url":"https://aclanthology.org/2024.findings-eacl.26.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: EACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.26","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.26","pdf_url":"https://aclanthology.org/2024.findings-eacl.26.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: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.472368448972702,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2761004381","display_name":"NFDI4DS  NFDI f\u00fcr Datenwissenschaften und K\u00fcnstliche Intelligenz","funder_award_id":"460234259","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7328517233","display_name":null,"funder_award_id":"01lS22070","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126444615.pdf","grobid_xml":"https://content.openalex.org/works/W7126444615.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"champion":[4],"the":[5,39,47,72,110,134,140],"use":[6],"of":[7,13,52],"structured":[8,24,56],"and":[9,65],"semantic":[10],"content":[11],"representation":[12],"discourse-based":[14],"scholarly":[15,57],"communication,":[16],"inspired":[17],"by":[18],"tools":[19],"like":[20,105],"Wikipedia":[21],"infoboxes":[22],"or":[23],"Amazon":[25],"product":[26],"descriptions.These":[27],"representations":[28],"provide":[29],"users":[30],"with":[31,117,129],"a":[32,62,118],"concise":[33],"overview,":[34],"aiding":[35],"scientists":[36],"in":[37,93,98],"navigating":[38],"dense":[40],"academic":[41],"landscape.Our":[42],"novel":[43],"automated":[44],"approach":[45,116],"leverages":[46],"robust":[48],"text":[49],"generation":[50],"capabilities":[51],"LLMs":[53],"to":[54],"produce":[55],"contribution":[58],"summaries,":[59],"offering":[60],"both":[61],"practical":[63],"solution":[64],"insights":[66],"into":[67],"LLMs'":[68],"emergent":[69],"abilities.For":[70],"LLMs,":[71],"prime":[73],"focus":[74],"is":[75,137],"on":[76],"improving":[77],"their":[78],"general":[79],"intelligence":[80],"as":[81],"conversational":[82],"agents.We":[83],"argue":[84],"that":[85,126],"these":[86],"models":[87],"can":[88],"also":[89],"be":[90],"applied":[91],"effectively":[92],"information":[94],"extraction":[95],"(IE),":[96],"specifically":[97],"complex":[99],"IE":[100],"tasks":[101],"within":[102],"terse":[103],"domains":[104],"Science.This":[106],"paradigm":[107],"shift":[108],"replaces":[109],"traditional":[111],"modular,":[112],"pipelined":[113],"machine":[114],"learning":[115],"simpler":[119],"objective":[120],"expressed":[121],"through":[122],"instructions.Our":[123],"results":[124],"show":[125],"finetuned":[127],"FLAN-T5":[128],"1000x":[130],"fewer":[131],"parameters":[132],"than":[133],"state-of-the-art":[135],"GPTdavinci":[136],"competitive":[138],"for":[139],"task.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2026-02-02T00:00:00"}