{"id":"https://openalex.org/W7143864882","doi":"https://doi.org/10.20736/0002002027","title":"KNUIR at the NTCIR-18 AEOLLM: Automatic Evaluation of LLMs","display_name":"KNUIR at the NTCIR-18 AEOLLM: Automatic Evaluation of LLMs","publication_year":null,"publication_date":null,"ids":{"openalex":"https://openalex.org/W7143864882","doi":"https://doi.org/10.20736/0002002027"},"language":"en","primary_location":{"id":"pmh:oai:irdb.nii.ac.jp:03100:0006839190","is_oa":true,"landing_page_url":"https://repository.nii.ac.jp/records/2002027","pdf_url":"https://repository.nii.ac.jp/record/2002027/files/03-NTCIR18-AEOLLM-KimY.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"},"type":"article","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.nii.ac.jp/record/2002027/files/03-NTCIR18-AEOLLM-KimY.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5131161415","display_name":"Yumi Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yumi Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080822884","display_name":"Meen Chul Kim","orcid":"https://orcid.org/0000-0002-0308-783X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meen Chul Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5131114321","display_name":"Jongwook Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jongwook Lee","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":"none","last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.2531999945640564,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.2531999945640564,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.21379999816417694,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.15569999814033508,"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/interpretability","display_name":"Interpretability","score":0.892799973487854},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6517000198364258},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4203999936580658},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4104999899864197},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4004000127315521},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.39320001006126404}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.892799973487854},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6517000198364258},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6172999739646912},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4203999936580658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4124000072479248},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4104999899864197},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40849998593330383},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.39320001006126404},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3862999975681305},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36800000071525574},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.35510000586509705},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C3019060180","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automated method","level":2,"score":0.274399995803833}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:irdb.nii.ac.jp:03100:0006839190","is_oa":true,"landing_page_url":"https://repository.nii.ac.jp/records/2002027","pdf_url":"https://repository.nii.ac.jp/record/2002027/files/03-NTCIR18-AEOLLM-KimY.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:03100:0006839190","is_oa":true,"landing_page_url":"https://repository.nii.ac.jp/records/2002027","pdf_url":"https://repository.nii.ac.jp/record/2002027/files/03-NTCIR18-AEOLLM-KimY.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.42778897285461426}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7143864882.pdf","grobid_xml":"https://content.openalex.org/works/W7143864882.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,50],"study,":[2],"we":[3,52,138],"aim":[4],"to":[5,76],"propose":[6],"automated":[7,156],"evaluation":[8,157],"methods":[9,113],"for":[10],"LLMs":[11,60],"that":[12,85,140],"approximate":[13],"human":[14,153],"judgment":[15,154],"by":[16],"exploring":[17],"and":[18,33,45,71,78,105,155],"comparing":[19],"two":[20,134],"distinct":[21],"approaches:":[22],"(1)":[23],"LLM-based":[24],"scoring,":[25],"which":[26],"utilizes":[27],"GPT":[28],"models":[29],"with":[30,110],"prompt":[31],"engineering,":[32],"(2)":[34],"feature-based":[35,98,120],"machine":[36],"learning,using":[37],"transformer-based":[38],"metrics":[39],"such":[40],"as":[41],"BERTScore,":[42],"semantic":[43],"similarity,":[44],"keyword":[46],"coverage.As":[47],"part":[48],"of":[49,59,66,143,152,158],"research,":[51],"participated":[53],"in":[54],"the":[55,64,67,72,80,89,93,97,130,133,136,141,150],"NTCIR-18":[56,77],"Automatic":[57],"Evaluation":[58],"(AE-OLLM)":[61],"task.We":[62],"submitted":[63],"results":[65,81,83],"test":[68],"data":[69,74],"set":[70,75],"reserved":[73],"analyzed":[79],"obtained.The":[82],"show":[84],"GPT-4o":[86,111],"Mini":[87],"(with":[88],"updated":[90],"prompt)":[91],"achieved":[92],"highest":[94],"performance,":[95],"while":[96],"approach":[99],"performed":[100],"competitively,":[101],"surpassing":[102],"GPT-3.5":[103],"Turbo":[104],"showing":[106],"a":[107],"small":[108],"gap":[109],"Mini.LLM-based":[112],"offered":[114],"scalability":[115],"but":[116,125],"lacked":[117],"explainability,":[118],"whereas":[119],"approaches":[121],"provided":[122],"better":[123],"interpretability":[124],"required":[126],"extensive":[127],"tuning,":[128],"highlighting":[129],"trade-offs":[131],"between":[132],"strategies.Throughout":[135],"analysis,":[137],"expect":[139],"findings":[142],"our":[144],"work":[145],"will":[146],"provide":[147],"insights":[148],"into":[149],"understanding":[151],"LLMs.":[159]},"counts_by_year":[],"updated_date":"2026-06-10T06:17:36.459440","created_date":"2026-04-01T00:00:00"}