{"id":"https://openalex.org/W7140128149","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.77","title":"Unsupervised Detection of LLM-Generated Text in Korean Using Syntactic and Semantic Cues","display_name":"Unsupervised Detection of LLM-Generated Text in Korean Using Syntactic and Semantic Cues","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140128149","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.77"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.77","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.77","pdf_url":"https://aclanthology.org/2026.findings-eacl.77.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: EACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.77.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029741137","display_name":"Heejeong Jeon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heejeong Jeon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100646726","display_name":"Minsu Park","orcid":"https://orcid.org/0000-0002-3995-4122"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"MinSu Park","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126966671","display_name":"YunSeok Choi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"YunSeok Choi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5047279790","display_name":"Eunil Park","orcid":"https://orcid.org/0000-0002-3177-3538"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eunil Park","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":"1504","last_page":"1518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.6241999864578247,"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":0.6241999864578247,"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/T10028","display_name":"Topic Modeling","score":0.08500000089406967,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.062300000339746475,"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/feature","display_name":"Feature (linguistics)","score":0.34360000491142273},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.33160001039505005},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2551000118255615},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.21690000593662262}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6545000076293945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6208999752998352},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5698000192642212},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.310699999332428},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.29829999804496765},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.21690000593662262},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2159000039100647}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.77","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.77","pdf_url":"https://aclanthology.org/2026.findings-eacl.77.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: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.77","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.77","pdf_url":"https://aclanthology.org/2026.findings-eacl.77.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: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3430829375","display_name":null,"funder_award_id":"RS-2024-00436936","funder_id":"https://openalex.org/F4320324891","funder_display_name":"Iran Telecommunication Research Center"},{"id":"https://openalex.org/G6470436729","display_name":null,"funder_award_id":"RS-2024-00436936","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140128149.pdf","grobid_xml":"https://content.openalex.org/works/W7140128149.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"are":[5],"increasingly":[6],"used":[7],"for":[8],"content":[9],"creation,":[10],"detecting":[11],"AI-generated":[12],"text":[13],"has":[14,20],"become":[15],"a":[16,55],"critical":[17],"challenge.Prior":[18],"work":[19],"largely":[21],"focused":[22],"on":[23],"English,":[24],"leaving":[25],"low-resource":[26,115],"languages":[27],"such":[28],"as":[29],"Korean":[30,56],"underexplored.We":[31],"propose":[32],"an":[33],"unsupervised":[34,112],"detection":[35,113],"framework":[36],"that":[37,102],"integrates":[38],"two":[39],"complementary":[40],"signals:":[41],"syntactic":[42,106],"token":[43],"cohesiveness":[44],"(TOCSIN)":[45],"and":[46,66,77,95,107],"semantic":[47,108],"regeneration":[48],"similarity":[49],"(SimLLM).To":[50],"support":[51],"evaluation,":[52],"we":[53],"construct":[54],"pairwise":[57],"dataset":[58],"of":[59,105],"1,000":[60],"anchors":[61],"with":[62],"continuationand":[63],"regeneration-style":[64],"generations":[65],"further":[67],"assess":[68],"performance":[69],"across":[70],"domains":[71],"(news,":[72],"research":[73],"paper":[74],"abstracts,":[75],"essays)":[76],"model":[78],"families":[79],"(GPT-3.5":[80],"Turbo,":[81],"GPT-4o,":[82],"HyperCLOVA":[83],"X,":[84],"LLaMA-3-8B).Without":[85],"any":[86],"training,":[87],"our":[88],"ensemble":[89],"achieves":[90],"up":[91],"to":[92],"0.963":[93],"F1":[94],"0.985":[96],"ROC-AUC,":[97],"outperforming":[98],"baselines.These":[99],"results":[100],"demonstrate":[101],"the":[103],"combination":[104],"cues":[109],"enables":[110],"robust":[111],"in":[114],"settings.":[116]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-24T00:00:00"}