{"id":"https://openalex.org/W4412888214","doi":"https://doi.org/10.18653/v1/2025.findings-acl.754","title":"EvoBench: Towards Real-world LLM-Generated Text Detection Benchmarking for Evolving Large Language Models","display_name":"EvoBench: Towards Real-world LLM-Generated Text Detection Benchmarking for Evolving Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888214","doi":"https://doi.org/10.18653/v1/2025.findings-acl.754"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.754","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.754","pdf_url":"https://aclanthology.org/2025.findings-acl.754.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: ACL 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-acl.754.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100321702","display_name":"Xiao Yu","orcid":"https://orcid.org/0009-0001-0924-6432"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068256019","display_name":"Yi Yu","orcid":"https://orcid.org/0000-0002-3922-6280"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020653216","display_name":"Dongrui Liu","orcid":"https://orcid.org/0000-0003-0087-1124"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongrui Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045121980","display_name":"Kejiang Chen","orcid":"https://orcid.org/0000-0002-9868-3414"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kejiang Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340737","display_name":"Weiming Zhang","orcid":"https://orcid.org/0000-0003-2609-2807"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiming Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064573190","display_name":"Nenghai Yu","orcid":"https://orcid.org/0000-0003-4417-9316"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nenghai Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103068380","display_name":"Jing Shao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Shao","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":"14605","last_page":"14620"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.991599977016449,"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":0.991599977016449,"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":0.9767000079154968,"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/benchmarking","display_name":"Benchmarking","score":0.8301992416381836},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.707243800163269},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5002243518829346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42376261949539185},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3467996120452881}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8301992416381836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.707243800163269},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5002243518829346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42376261949539185},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3467996120452881},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.754","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.754","pdf_url":"https://aclanthology.org/2025.findings-acl.754.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: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.754","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.754","pdf_url":"https://aclanthology.org/2025.findings-acl.754.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: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3061771244","display_name":null,"funder_award_id":"62472398","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4538375728","display_name":null,"funder_award_id":"U2336206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888214.pdf","grobid_xml":"https://content.openalex.org/works/W4412888214.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W3204019825"],"abstract_inverted_index":{"With":[0],"the":[1,34,51,77,102,137,150],"widespread":[2],"of":[3,37,48,54,70,117],"Large":[4],"Language":[5],"Models":[6],"(LLMs),":[7],"there":[8],"has":[9],"been":[10],"an":[11],"increasing":[12],"need":[13],"to":[14,128,153],"detect":[15],"LLM-generated":[16,174],"texts,":[17],"prompting":[18],"extensive":[19],"research":[20,166],"in":[21,172],"this":[22,58],"area.However,":[23],"existing":[24,40],"detection":[25,55,119,176],"methods":[26,120],"mainly":[27],"evaluate":[28],"on":[29,39,121,169],"static":[30,41],"benchmarks,":[31],"which":[32],"neglect":[33],"evolving":[35,74,78,99,105,134],"nature":[36],"LLMs.Relying":[38],"benchmarks":[42],"could":[43],"create":[44],"a":[45,63,67,109,162,179],"misleading":[46],"sense":[47],"security,":[49],"overestimating":[50],"real-world":[52,173],"effectiveness":[53],"methods.To":[56],"bridge":[57],"gap,":[59],"we":[60,107,140,147,159],"introduce":[61,108],"EvoBench,":[62],"dynamic":[64],"benchmark":[65],"considering":[66],"new":[68,110],"dimension":[69],"generalization":[71,103,130,138],"across":[72,104],"continuously":[73],"LLMs.EvoBench":[75],"categorizes":[76],"LLMs":[79],"into":[80],"(1)":[81],"updates":[82],"over":[83],"time":[84],"and":[85,90,96,177],"(2)":[86],"developments":[87],"like":[88],"finetuning":[89],"pruning,":[91],"covering":[92],"7":[93],"LLM":[94],"families":[95],"their":[97],"29":[98],"versions.To":[100],"measure":[101],"LLMs,":[106],"EMG":[111],"(Evolving":[112],"Model":[113],"Generalization)":[114],"metric.Our":[115],"evaluation":[116],"14":[118],"EvoBench":[122],"reveals":[123],"that":[124],"they":[125],"all":[126],"struggle":[127],"maintain":[129],"when":[131],"confronted":[132],"with":[133],"LLMs.To":[135],"mitigate":[136],"problems,":[139],"further":[141],"propose":[142,148,161],"improvement":[143],"strategies.For":[144],"zero-shot":[145],"detectors,":[146,158],"pruning":[149],"scoring":[151],"model":[152],"extract":[154],"shared":[155],"features.For":[156],"supervised":[157],"also":[160],"practical":[163,183],"training":[164],"strategy.Our":[165],"sheds":[167],"light":[168],"critical":[170],"challenges":[171],"text":[175],"represents":[178],"significant":[180],"step":[181],"toward":[182],"applications.The":[184],"Evobench":[185],"is":[186],"now":[187],"available":[188],"at:":[189],"https://github.com/happy-Moer/EvoBench.":[190]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}