{"id":"https://openalex.org/W7166544620","doi":"https://doi.org/10.63317/5inv25yddbgv","title":"Evaluating Generative Large Language Models for Portuguese Scientific Information Extraction","display_name":"Evaluating Generative Large Language Models for Portuguese Scientific Information Extraction","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7166544620","doi":"https://doi.org/10.63317/5inv25yddbgv"},"language":null,"primary_location":{"id":"doi:10.63317/5inv25yddbgv","is_oa":true,"landing_page_url":"https://doi.org/10.63317/5inv25yddbgv","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nslp/pdf/2026.nslp-1.15.pdf","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nslp/pdf/2026.nslp-1.15.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133648668","display_name":"Tom\u00e1s Pinto","orcid":"https://orcid.org/0009-0004-7785-3543"},"institutions":[{"id":"https://openalex.org/I76903346","display_name":"University of Coimbra","ror":"https://ror.org/04z8k9a98","country_code":"PT","type":"education","lineage":["https://openalex.org/I76903346"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Tom\u00e1s Pinto","raw_affiliation_strings":["University of Coimbra , CISUC/LASI , DEI , Coimbra , Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Coimbra , CISUC/LASI , DEI , Coimbra , Portugal","institution_ids":["https://openalex.org/I76903346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371897","display_name":"Catarina Silva","orcid":"https://orcid.org/0000-0002-5656-0061"},"institutions":[{"id":"https://openalex.org/I76903346","display_name":"University of Coimbra","ror":"https://ror.org/04z8k9a98","country_code":"PT","type":"education","lineage":["https://openalex.org/I76903346"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Catarina Silva","raw_affiliation_strings":["University of Coimbra , CISUC/LASI , DEI , Coimbra , Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Coimbra , CISUC/LASI , DEI , Coimbra , Portugal","institution_ids":["https://openalex.org/I76903346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135213749","display_name":"Hugo Goncalo Oliveira","orcid":null},"institutions":[{"id":"https://openalex.org/I76903346","display_name":"University of Coimbra","ror":"https://ror.org/04z8k9a98","country_code":"PT","type":"education","lineage":["https://openalex.org/I76903346"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Hugo Goncalo Oliveira","raw_affiliation_strings":["University of Coimbra , CISUC/LASI , DEI , Coimbra , Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Coimbra , CISUC/LASI , DEI , Coimbra , Portugal","institution_ids":["https://openalex.org/I76903346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76903346"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.76526758,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"155","last_page":"167"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6904000043869019,"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":0.6904000043869019,"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":0.08190000057220459,"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":0.06210000067949295,"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/generative-grammar","display_name":"Generative grammar","score":0.7106000185012817},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.678600013256073},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.6525999903678894},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.510200023651123},{"id":"https://openalex.org/keywords/portuguese","display_name":"Portuguese","score":0.48339998722076416},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.46470001339912415},{"id":"https://openalex.org/keywords/scientific-modelling","display_name":"Scientific modelling","score":0.4399000108242035},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.40779998898506165},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4058000147342682}],"concepts":[{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7106000185012817},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7024999856948853},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.678600013256073},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.6525999903678894},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5490000247955322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5196999907493591},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.510200023651123},{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.48339998722076416},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.46470001339912415},{"id":"https://openalex.org/C138379479","wikidata":"https://www.wikidata.org/wiki/Q1116876","display_name":"Scientific modelling","level":2,"score":0.4399000108242035},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4140999913215637},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.40779998898506165},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4027000069618225},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3887999951839447},{"id":"https://openalex.org/C195732255","wikidata":"https://www.wikidata.org/wiki/Q981008","display_name":"Sociology of scientific knowledge","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.32829999923706055},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.3176000118255615},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3125},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.3061999976634979},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C2778880076","wikidata":"https://www.wikidata.org/wiki/Q750553","display_name":"Brazilian Portuguese","level":3,"score":0.2971000075340271},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27000001072883606},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.25200000405311584},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.63317/5inv25yddbgv","is_oa":true,"landing_page_url":"https://doi.org/10.63317/5inv25yddbgv","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nslp/pdf/2026.nslp-1.15.pdf","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.63317/5inv25yddbgv","is_oa":true,"landing_page_url":"https://doi.org/10.63317/5inv25yddbgv","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nslp/pdf/2026.nslp-1.15.pdf","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49882349371910095}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166544620.pdf","grobid_xml":"https://content.openalex.org/works/W7166544620.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Scientific":[0,17],"Information":[1],"Extraction":[2,99],"(IE),":[3],"which":[4],"identifies":[5],"entities":[6],"and":[7,25,34,97,115,142,144,161,173],"their":[8],"relations":[9],"from":[10,79],"scientific":[11,77,92,179],"texts,":[12],"is":[13,156],"essential":[14],"for":[15,57,73,158,165,176],"building":[16],"Knowledge":[18],"Graphs":[19],"(SciKGs)":[20],"that":[21,117],"encode":[22],"structured":[23,74],"knowledge":[24,78],"enable":[26],"applications":[27],"such":[28],"as":[29],"semantic":[30],"search,":[31],"question":[32],"answering,":[33],"literature":[35,80],"reasoning.Large":[36],"Language":[37],"Models":[38],"(LLMs)":[39],"have":[40],"shown":[41],"strong":[42],"capabilities":[43],"in":[44],"processing":[45],"unstructured":[46],"text,":[47],"yet":[48],"most":[49],"advances":[50],"focus":[51],"on":[52,91],"English,":[53],"with":[54,132],"limited":[55],"exploration":[56],"less-resourced":[58],"languages":[59],"like":[60,69],"Portuguese.The":[61],"reliability":[62],"of":[63,76,105],"generative":[64,87],"LLMs,":[65],"including":[66],"Portuguese-targeted":[67],"models":[68],"the":[70,118,163],"sovereign":[71],"AMALIA,":[72],"extraction":[75],"text":[81],"remains":[82],"underexplored.We":[83],"evaluate":[84],"low-to":[85],"mid-scale":[86],"LLMs":[88],"(8-12B":[89],"parameters)":[90],"Named":[93],"Entity":[94],"Recognition":[95],"(NER)":[96],"Relation":[98],"(RE),":[100],"using":[101],"a":[102,122,169],"Portuguese-translated":[103],"dataset":[104],"computer":[106],"science":[107],"article":[108],"abstracts.Overall,":[109],"our":[110],"results":[111],"show":[112],"moderate":[113],"performance":[114,131],"indicate":[116],"adaptation":[119],"strategy":[120],"has":[121],"greater":[123],"impact":[124],"than":[125],"model":[126],"choice:":[127],"prompting":[128,154],"yields":[129],"unstable":[130],"poor":[133],"RE":[134,143],"scores,":[135],"while":[136],"fine-tuning":[137],"consistently":[138],"improves":[139],"both":[140],"NER":[141],"reduces":[145],"cross-model":[146],"variability.These":[147],"findings":[148],"suggest":[149],"that,":[150],"at":[151],"this":[152],"scale,":[153],"alone":[155],"insufficient":[157],"SciKG":[159],"construction":[160],"underscore":[162],"need":[164],"supervised":[166],"adaptation.We":[167],"provide":[168],"detailed":[170],"error":[171],"analysis":[172],"outline":[174],"directions":[175],"advancing":[177],"Portuguese":[178],"IE.":[180]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-06-30T00:00:00"}