{"id":"https://openalex.org/W4417493421","doi":"https://doi.org/10.63317/539pqaksijax","title":"Evaluating Text Style Transfer: A Nine-language Benchmark for Text Detoxification","display_name":"Evaluating Text Style Transfer: A Nine-language Benchmark for Text Detoxification","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W4417493421","doi":"https://doi.org/10.63317/539pqaksijax"},"language":"en","primary_location":{"id":"doi:10.63317/539pqaksijax","is_oa":false,"landing_page_url":"https://doi.org/10.63317/539pqaksijax","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.15557","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010767743","display_name":"Vitaly Protasov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vitaly Protasov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010164860","display_name":"Nikolay Babakov","orcid":"https://orcid.org/0000-0002-2568-6702"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolay Babakov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043273387","display_name":"Daryna Dementieva","orcid":"https://orcid.org/0000-0003-0929-4140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daryna Dementieva","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026157285","display_name":"Alexander Panchenko","orcid":"https://orcid.org/0000-0001-6097-6118"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Panchenko","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03898539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4560","last_page":"4574"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.32089999318122864,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.32089999318122864,"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/T13629","display_name":"Text Readability and Simplification","score":0.24889999628067017,"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":0.1160999983549118,"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":0.6251999735832214},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5498999953269958},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.43700000643730164},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4198000133037567},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4092999994754791},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.37389999628067017},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.35760000348091125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6800000071525574},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6251999735832214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6035000085830688},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5498999953269958},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5486000180244446},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5324000120162964},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.43700000643730164},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4198000133037567},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.29190000891685486},{"id":"https://openalex.org/C2779525943","wikidata":"https://www.wikidata.org/wiki/Q1187300","display_name":"Grammaticality","level":3,"score":0.272599995136261},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2653000056743622},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2632000148296356},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.258899986743927}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.63317/539pqaksijax","is_oa":false,"landing_page_url":"https://doi.org/10.63317/539pqaksijax","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.15557","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15557","pdf_url":"https://arxiv.org/pdf/2507.15557","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.15557","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.15557","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.15557","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15557","pdf_url":"https://arxiv.org/pdf/2507.15557","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417493421.pdf","grobid_xml":"https://content.openalex.org/works/W4417493421.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"notable":[1],"advances":[2],"in":[3],"large":[4],"language":[5],"models":[6],"(LLMs),":[7],"reliable":[8,158],"evaluation":[9,64,88,93,160],"of":[10,65,87],"text":[11,16,71,91,163],"generation":[12],"tasks":[13],"such":[14],"as":[15],"style":[17],"transfer":[18],"(TST)":[19],"remains":[20,73],"an":[21],"open":[22],"challenge.":[23],"Existing":[24],"research":[25],"has":[26,57],"shown":[27],"that":[28,131],"automatic":[29,116],"metrics":[30,89,117,134],"often":[31],"correlate":[32],"poorly":[33],"with":[34,118,122,139],"human":[35,140],"judgments":[36,141],"(Dementieva":[37],"et":[38,42],"al.,":[39,43],"2024;":[40],"Pauli":[41],"2025),":[44],"limiting":[45],"our":[46],"ability":[47],"to":[48,143],"assess":[49],"model":[50],"performance":[51],"accurately.":[52],"Furthermore,":[53],"most":[54],"prior":[55],"work":[56],"focused":[58],"primarily":[59],"on":[60,124],"English,":[61,100],"while":[62],"the":[63,81,132],"multilingual":[66,84,159],"TST":[67,167],"systems,":[68],"particularly":[69],"for":[70,90,154,162],"detoxification,":[72],"largely":[74],"underexplored.":[75],"In":[76],"this":[77],"paper,":[78],"we":[79,113],"present":[80],"first":[82],"comprehensive":[83],"benchmarking":[85],"study":[86],"detoxification":[92,164],"across":[94],"nine":[95],"languages:":[96],"Arabic,":[97],"Amharic,":[98],"Chinese,":[99],"German,":[101],"Hindi,":[102],"Russian,":[103],"Spanish,":[104],"and":[105,151,157,165],"Ukrainian.":[106],"Drawing":[107],"inspiration":[108],"from":[109],"machine":[110],"translation":[111],"evaluation,":[112],"compare":[114],"neural-based":[115],"LLM-as-a-judge":[119],"approaches":[120],"together":[121],"experiments":[123],"task-specific":[125],"fine-tuned":[126],"models.":[127],"Our":[128],"analysis":[129],"reveals":[130],"proposed":[133],"achieve":[135],"significantly":[136],"higher":[137],"correlation":[138],"compared":[142],"baseline":[144],"approaches.":[145],"We":[146],"also":[147],"provide":[148],"actionable":[149],"insights":[150],"practical":[152],"guidelines":[153],"building":[155],"robust":[156],"pipelines":[161],"related":[166],"tasks.":[168]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}