{"id":"https://openalex.org/W4416034235","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.938","title":"Ko-LongRAG: A Korean Long-Context RAG Benchmark Built with a Retrieval-Free Approach","display_name":"Ko-LongRAG: A Korean Long-Context RAG Benchmark Built with a Retrieval-Free Approach","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034235","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.938"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.938","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.938","pdf_url":"https://aclanthology.org/2025.findings-emnlp.938.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.938.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101964120","display_name":"Yongil Kim","orcid":"https://orcid.org/0000-0003-0541-8986"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongil Kim","raw_affiliation_strings":["LG AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LG AI Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120308520","display_name":"Heuiyeen Yeen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heuiyeen Yeen","raw_affiliation_strings":["LG AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LG AI Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044469790","display_name":"Hyeongu Yun","orcid":"https://orcid.org/0000-0002-1506-6200"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyeongu Yun","raw_affiliation_strings":["LG AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LG AI Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058978491","display_name":"Jinsik Lee","orcid":"https://orcid.org/0000-0002-1040-0513"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinsik Lee","raw_affiliation_strings":["LG AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LG AI Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.29785054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17317","last_page":"17329"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.23389999568462372,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.23389999568462372,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.05700000002980232,"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/T12031","display_name":"Speech and dialogue systems","score":0.03830000013113022,"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/benchmark","display_name":"Benchmark (surveying)","score":0.3752000033855438},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3028999865055084},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.2621999979019165},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.250900000333786},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.24169999361038208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6421999931335449},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33059999346733093},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25760000944137573},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.250900000333786},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.24169999361038208},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.2387000024318695},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.23340000212192535}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.938","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.938","pdf_url":"https://aclanthology.org/2025.findings-emnlp.938.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.938","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.938","pdf_url":"https://aclanthology.org/2025.findings-emnlp.938.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034235.pdf","grobid_xml":"https://content.openalex.org/works/W4416034235.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"significantly":[8],"enhances":[9],"long-context":[10,43,109],"Retrieval-Augmented":[11],"Generation":[12],"(RAG),":[13],"yet":[14],"existing":[15],"benchmarks":[16,47],"focus":[17],"primarily":[18],"on":[19,50],"English.This":[20],"leaves":[21],"low-resource":[22],"languages":[23],"without":[24,71],"comprehensive":[25],"evaluation":[26,79],"frameworks,":[27],"limiting":[28],"their":[29],"progress":[30],"in":[31],"retrieval-based":[32],"tasks.To":[33],"bridge":[34],"this":[35],"gap,":[36],"we":[37],"introduce":[38],"Ko-LongRAG,":[39],"the":[40,72,85],"first":[41],"Korean":[42,108],"RAG":[44,110,119],"benchmark.Unlike":[45],"conventional":[46],"that":[48,81],"depend":[49],"external":[51],"retrievers,":[52],"Ko-LongRAG":[53,101],"adopts":[54],"a":[55,103],"retrieval-free":[56],"approach":[57],"designed":[58],"around":[59],"Specialized":[60],"Content":[61],"Knowledge":[62],"(SCK),":[63],"enabling":[64],"controlled":[65],"and":[66,112],"high-quality":[67],"QA":[68],"pair":[69],"generation":[70],"need":[73],"for":[74,106,116],"an":[75],"extensive":[76],"retrieval":[77],"infrastructure.Our":[78],"shows":[80],"o1":[82],"model":[83],"achieves":[84],"highest":[86],"performance":[87],"among":[88,95],"proprietary":[89],"models,":[90],"while":[91],"EXAONE":[92],"3.5":[93],"leads":[94],"open-sourced":[96],"models.Additionally,":[97],"various":[98],"findings":[99],"confirm":[100],"as":[102],"reliable":[104],"benchmark":[105],"assessing":[107],"capabilities":[111],"highlight":[113],"its":[114],"potential":[115],"advancing":[117],"multilingual":[118],"research.":[120]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}