{"id":"https://openalex.org/W7126402336","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.43","title":"Capturing the Relationship Between Sentence Triplets for LLM and Human-Generated Texts to Enhance Sentence Embeddings","display_name":"Capturing the Relationship Between Sentence Triplets for LLM and Human-Generated Texts to Enhance Sentence Embeddings","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126402336","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.43"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.43","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.43","pdf_url":"https://aclanthology.org/2024.findings-eacl.43.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 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.43.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124575864","display_name":"Na Min An","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Na Min An","raw_affiliation_strings":["KAIST AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST AI","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042236101","display_name":"Sania Waheed","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Sania Waheed","raw_affiliation_strings":["KAIST AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST AI","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124661267","display_name":"James Thorne","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"James Thorne","raw_affiliation_strings":["KAIST AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST AI","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.57257102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"624","last_page":"638"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.42640000581741333,"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/T10028","display_name":"Topic Modeling","score":0.42640000581741333,"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":0.11010000109672546,"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":0.08569999784231186,"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/sentence","display_name":"Sentence","score":0.7052000164985657},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.352400004863739},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.23489999771118164},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.2273000031709671}],"concepts":[{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7052000164985657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5992000102996826},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5651999711990356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.564300000667572},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4262999892234802},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25760000944137573},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.23489999771118164},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2273000031709671},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.21950000524520874}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.43","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.43","pdf_url":"https://aclanthology.org/2024.findings-eacl.43.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 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.43","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.43","pdf_url":"https://aclanthology.org/2024.findings-eacl.43.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 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1769687045","display_name":null,"funder_award_id":"2019-0-00075","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G2148870006","display_name":null,"funder_award_id":"2019-0-00075","funder_id":"https://openalex.org/F4320324161","funder_display_name":"Korea Advanced Institute of Science and Technology"},{"id":"https://openalex.org/G4628738581","display_name":null,"funder_award_id":"No. 2019-0-00075","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G5415505637","display_name":null,"funder_award_id":"2019-0-00075","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320324161","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63"},{"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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126402336.pdf","grobid_xml":"https://content.openalex.org/works/W7126402336.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deriving":[0],"meaningful":[1],"sentence":[2,16,95,129,133],"embeddings":[3],"is":[4,160],"crucial":[5],"in":[6,14,121,136,148],"capturing":[7],"the":[8,32,45,48,69,110,116,132,145],"semantic":[9],"relationship":[10],"between":[11],"texts.Recent":[12],"advances":[13],"building":[15],"embedding":[17],"models":[18,87],"have":[19],"centered":[20],"on":[21],"replacing":[22],"traditional":[23],"human-generated":[24],"text":[25],"datasets":[26],"with":[27,90,98],"those":[28],"generated":[29],"by":[30,123],"LLMs.However,":[31],"properties":[33],"of":[34,47,71,85,118],"these":[35,86],"widely":[36],"used":[37],"LLMgenerated":[38,49],"texts":[39,50],"remain":[40],"largely":[41],"unexplored.Here,":[42],"we":[43,80],"evaluate":[44],"quality":[46],"from":[51],"four":[52],"perspectives":[53],"(Positive":[54],"Text":[55,65],"Repetition,":[56],"Length":[57],"Difference":[58],"Penalty,":[59],"Positive":[60],"Score":[61],"Compactness,":[62],"and":[63,67,143],"Negative":[64],"Implausibility)":[66],"find":[68],"limitation":[70],"only":[72],"using":[73],"LLM":[74],"to":[75,82,141,157],"build":[76],"high-quality":[77],"NLI":[78],"datasets.Then,":[79],"attempt":[81],"improve":[83],"each":[84],"either":[88],"fine-tuned":[89],"human,":[91],"LLM,":[92],"or":[93],"human+LLM-generated":[94],"triplets":[96],"data":[97],"our":[99],"proposed":[100],"loss":[101],"function":[102],"that":[103],"incorporates":[104],"Positive-Negative":[105],"sample":[106],"Augmentation":[107],"(PNA)":[108],"within":[109],"contrastive":[111],"learning":[112],"objective.Our":[113],"results":[114],"demonstrate":[115],"effectiveness":[117],"PNA,":[119],"especially":[120],"RoBERTalarge,":[122],"showing":[124],"decreased":[125],"cosine":[126],"similarity":[127],"for":[128],"triplets,":[130],"mitigating":[131],"anisotropy":[134],"problem":[135],"Wikipedia":[137],"corpus":[138],"(-7%":[139],"compared":[140,156],"CLHAIF),":[142],"improving":[144],"Spearman's":[146],"correlation":[147],"standard":[149],"Semantic":[150],"Textual":[151],"Similarity":[152],"(STS)":[153],"tasks":[154],"(+1.47%":[155],"CLHAIF).Our":[158],"code":[159],"available":[161],"at":[162],"https://github.com/xfactlab/eacl2024-pna.":[163]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-02T00:00:00"}