{"id":"https://openalex.org/W7047254261","doi":null,"title":"Evaluating the accuracy of large language models for text summarization in Finnish","display_name":"Evaluating the accuracy of large language models for text summarization in Finnish","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7047254261"},"language":"en","primary_location":{"id":"pmh:oai:lutpub.lut.fi:10024/169636","doi":null,"is_oa":true,"landing_page_url":"https://lutpub.lut.fi/handle/10024/169636","pdf_url":"https://lutpub.lut.fi/bitstream/10024/169636/1/mastersthesis_ataei_maryam.pdf","source":{"id":"https://openalex.org/S4306402474","display_name":"LUTPub (LUT University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63548447","host_organization_name":"Lappeenranta-Lahti University of Technology","host_organization_lineage":["https://openalex.org/I63548447"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"fi=Diplomity\u00f6|en=Master's thesis|"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://lutpub.lut.fi/bitstream/10024/169636/1/mastersthesis_ataei_maryam.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ataei, Maryam","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ataei, Maryam","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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9541000127792358,"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":0.9541000127792358,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.027000000700354576,"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":0.01269999984651804,"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/large-language-models","display_name":"large language models","score":0.9860000014305115},{"id":"https://openalex.org/keywords/summarization-evaluation","display_name":"summarization evaluation","score":0.7549999952316284},{"id":"https://openalex.org/keywords/morphologically-rich-languages","display_name":"morphologically rich languages","score":0.6769999861717224},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.8880000114440918},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.8090000152587891},{"id":"https://openalex.org/keywords/deepseek","display_name":"DeepSeek","score":0.7940000295639038},{"id":"https://openalex.org/keywords/poros","display_name":"Poros","score":0.9139999747276306},{"id":"https://openalex.org/keywords/chrf","display_name":"chrF","score":0.6890000104904175},{"id":"https://openalex.org/keywords/bertscore","display_name":"BERTScore","score":0.7670000195503235},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"cosine similarity","score":0.921999990940094},{"id":"https://openalex.org/keywords/journal-abstracts","display_name":"journal abstracts","score":0.597000002861023},{"id":"https://openalex.org/keywords/multilingual-models","display_name":"multilingual models","score":0.4580000042915344}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8303999900817871},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7394999861717224},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6589000225067139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6237000226974487},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5605999827384949},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5471000075340271},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.48030000925064087},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.47290000319480896},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43459999561309814},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4242999851703644},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32010000944137573},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.299699991941452},{"id":"https://openalex.org/C159403335","wikidata":"https://www.wikidata.org/wiki/Q207857","display_name":"Inflection","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:lutpub.lut.fi:10024/169636","doi":null,"is_oa":true,"landing_page_url":"https://lutpub.lut.fi/handle/10024/169636","pdf_url":"https://lutpub.lut.fi/bitstream/10024/169636/1/mastersthesis_ataei_maryam.pdf","source":{"id":"https://openalex.org/S4306402474","display_name":"LUTPub (LUT University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63548447","host_organization_name":"Lappeenranta-Lahti University of Technology","host_organization_lineage":["https://openalex.org/I63548447"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"fi=Diplomity\u00f6|en=Master's thesis|"}],"best_oa_location":{"id":"pmh:oai:lutpub.lut.fi:10024/169636","doi":null,"is_oa":true,"landing_page_url":"https://lutpub.lut.fi/handle/10024/169636","pdf_url":"https://lutpub.lut.fi/bitstream/10024/169636/1/mastersthesis_ataei_maryam.pdf","source":{"id":"https://openalex.org/S4306402474","display_name":"LUTPub (LUT University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63548447","host_organization_name":"Lappeenranta-Lahti University of Technology","host_organization_lineage":["https://openalex.org/I63548447"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"fi=Diplomity\u00f6|en=Master's thesis|"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7047254261.pdf","grobid_xml":"https://content.openalex.org/works/W7047254261.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2110693578","https://openalex.org/W2161792612","https://openalex.org/W2169353679","https://openalex.org/W2250342921","https://openalex.org/W2733964180","https://openalex.org/W2758950307","https://openalex.org/W2970807214","https://openalex.org/W3030163527","https://openalex.org/W4206584443","https://openalex.org/W4310378682","https://openalex.org/W4393933640","https://openalex.org/W4409083639","https://openalex.org/W4415829728","https://openalex.org/W7090618716"],"related_works":["https://openalex.org/W7137780040","https://openalex.org/W4417456796","https://openalex.org/W4388650609","https://openalex.org/W7220561224","https://openalex.org/W7052162863","https://openalex.org/W7118015698","https://openalex.org/W7043625517","https://openalex.org/W4406660386","https://openalex.org/W7116602801","https://openalex.org/W7213612960"],"abstract_inverted_index":{"This":[0],"thesis":[1],"investigates":[2],"the":[3,23,30,50,93,98,125,147,154,188,199],"performance":[4,200],"of":[5,26,36,83,100,156,190,201],"large":[6,167],"language":[7,168],"models":[8,180,203],"in":[9,70,159,181],"Finnish":[10,84,182],"text":[11],"summarization":[12,183],"by":[13,105],"comparing":[14],"three":[15,107],"models:":[16],"Poro,":[17],"DeepSeek,":[18],"and":[19,29,55,67],"OpenAI":[20,128],"o3mini.":[21],"Given":[22],"high":[24],"degree":[25],"morphological":[27],"inflection":[28],"relatively":[31],"free":[32],"word":[33],"order":[34],"characteristic":[35],"Finnish,":[37],"conventional":[38],"evaluation":[39,76],"metrics":[40,58],"often":[41],"fail":[42],"to":[43,60,113,197],"capture":[44],"content":[45],"equivalence.":[46],"To":[47],"address":[48],"this,":[49],"study":[51,186],"adopts":[52],"chrf,":[53],"bertscore,":[54],"cosine":[56],"similarity":[57,69],"demonstrated":[59],"be":[61],"more":[62],"reliable":[63],"for":[64],"evaluating":[65],"lexical":[66],"semantic":[68],"low-resource,":[71],"morphologically":[72],"complex":[73],"languages.":[74],"The":[75,139,185],"is":[77,90,103],"conducted":[78],"on":[79],"a":[80,194],"curated":[81],"set":[82],"academic":[85],"articles.":[86],"Each":[87],"model-generated":[88],"summary":[89],"compared":[91],"against":[92],"corresponding":[94],"human-written":[95],"abstract.":[96],"Furthermore,":[97],"impact":[99],"prompt":[101,108,141,157,191],"engineering":[102,192],"examined":[104],"testing":[106],"variations,":[109],"ranging":[110],"from":[111],"generic":[112],"domain-specific,":[114],"including":[115],"expert-role":[116],"conditioning.":[117],"Empirical":[118],"results":[119,149],"show":[120],"that":[121,165],"DeepSeek":[122],"consistently":[123],"achieves":[124],"highest":[126],"performance.":[127],"o3mini":[129],"performs":[130],"moderately":[131],"well,":[132],"while":[133],"Poro":[134],"underperforms":[135],"across":[136,150],"all":[137,151],"metrics.":[138],"structured":[140],"incorporating":[142],"expert":[143],"role":[144],"instructions":[145],"yields":[146],"best":[148],"models,":[152,169],"highlighting":[153],"importance":[155],"formulation":[158],"low-resource":[160],"contexts.":[161],"These":[162],"findings":[163],"suggest":[164],"multilingual":[166],"when":[170],"guided":[171],"with":[172],"carefully":[173],"designed":[174],"prompts,":[175],"can":[176],"outperform":[177],"smaller":[178],"domain-specific":[179],"tasks.":[184],"underscores":[187],"value":[189],"as":[193],"cost-effective":[195],"strategy":[196],"enhance":[198],"general-purpose":[202],"without":[204],"additional":[205],"fine-tuning.":[206]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}