{"id":"https://openalex.org/W7166546099","doi":"https://doi.org/10.63317/3muergicuxwk","title":"Benchmarking Retrieval-Augmented Generation for Scientific Knowledge QA in European Portuguese","display_name":"Benchmarking Retrieval-Augmented Generation for Scientific Knowledge QA in European Portuguese","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7166546099","doi":"https://doi.org/10.63317/3muergicuxwk"},"language":null,"primary_location":{"id":"doi:10.63317/3muergicuxwk","is_oa":true,"landing_page_url":"https://doi.org/10.63317/3muergicuxwk","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nslp/pdf/2026.nslp-1.3.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-1.3.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139583574","display_name":"Jose Matos","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":"Jose Matos","raw_affiliation_strings":["DEI , University of Coimbra , Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DEI , University of 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":["DEI , University of Coimbra , Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DEI , University of 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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hugo Goncalo Oliveira","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.76563996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5019999742507935,"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":0.5019999742507935,"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":0.16220000386238098,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.1565999984741211,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/portuguese","display_name":"Portuguese","score":0.8949000239372253},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8246999979019165},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6363000273704529},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.5957000255584717},{"id":"https://openalex.org/keywords/european-portuguese","display_name":"European Portuguese","score":0.4334999918937683},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4187999963760376}],"concepts":[{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.8949000239372253},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8246999979019165},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6363000273704529},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.5957000255584717},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5468999743461609},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4726000130176544},{"id":"https://openalex.org/C2780939345","wikidata":"https://www.wikidata.org/wiki/Q922399","display_name":"European Portuguese","level":3,"score":0.4334999918937683},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.41659998893737793},{"id":"https://openalex.org/C195732255","wikidata":"https://www.wikidata.org/wiki/Q981008","display_name":"Sociology of scientific knowledge","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.37450000643730164},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2809999883174896},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.63317/3muergicuxwk","is_oa":true,"landing_page_url":"https://doi.org/10.63317/3muergicuxwk","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nslp/pdf/2026.nslp-1.3.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:10.63317/3muergicuxwk","is_oa":true,"landing_page_url":"https://doi.org/10.63317/3muergicuxwk","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nslp/pdf/2026.nslp-1.3.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":[{"display_name":"Quality Education","score":0.7985103726387024,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166546099.pdf","grobid_xml":"https://content.openalex.org/works/W7166546099.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieval-Augmented":[0],"Generation":[1],"(RAG)":[2],"enables":[3],"grounding":[4],"of":[5,28,43,97,132,137],"model":[6],"outputs":[7],"in":[8],"external":[9,49],"evidence,":[10,50],"but":[11],"its":[12],"impact":[13],"on":[14,30],"European":[15],"Portuguese":[16,40,54,157],"(pt-PT)":[17],"scientific":[18,36,55,159],"question":[19],"answering":[20],"(QA)":[21],"remains":[22],"unclear.We":[23],"present":[24],"a":[25,53],"controlled":[26],"evaluation":[27],"RAG":[29,79,108,154],"pt-PT":[31],"knowledge":[32,57],"QA":[33],"across":[34],"different":[35],"domains":[37,150],"using":[38],"the":[39,44,135,144],"test":[41],"split":[42],"Global":[45],"MMLU":[46],"Lite":[47],"dataset.As":[48],"we":[51],"use":[52],"literature":[56],"base":[58],"containing":[59],"over":[60],"32,000":[61],"documents":[62],"converted":[63],"to":[64,119],"Markdown.We":[65],"benchmark":[66],"five":[67],"instruction-tuned":[68],"small":[69],"language":[70,160],"models":[71,112],"(4-12B)":[72],"and":[73,94,122,141,146,149],"compare":[74],"closed-book":[75],"baselines":[76],"against":[77],"16":[78],"configurations":[80],"that":[81,107,143],"vary":[82],"by:":[83],"(i)":[84],"dense":[85],"retriever":[86,145],"specialization":[87],"(multilingual":[88],"vs.":[89],"Portuguese-specific),":[90],"(ii)":[91],"reranking":[92],"(on/off),":[93],"(iii)":[95],"number":[96],"retrieved":[98],"chunks":[99],"(k":[100],"\u2208":[101],"{1,":[102],"3,":[103],"5,":[104],"10}).Results":[105],"suggest":[106],"gains":[109],"are":[110,116],"model-dependent.Some":[111],"improve":[113],"consistently,":[114],"others":[115],"highly":[117],"sensitive":[118],"retrieval":[120,126,139],"choices,":[121],"some":[123],"degrade":[124],"under":[125],"noise,":[127],"especially":[128],"at":[129],"larger":[130],"values":[131],"k.Findings":[133],"highlight":[134],"importance":[136],"model-specific":[138],"tuning":[140],"ensuring":[142],"reranker":[147],"languages":[148],"align":[151],"when":[152],"deploying":[153],"systems":[155],"for":[156],"natural":[158],"processing.":[161]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-06-30T00:00:00"}
