{"id":"https://openalex.org/W4412887723","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1160","title":"Understanding the Influence of Synthetic Data for Text Embedders","display_name":"Understanding the Influence of Synthetic Data for Text Embedders","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887723","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1160"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1160","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1160","pdf_url":"https://aclanthology.org/2025.findings-acl.1160.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.1160.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035773495","display_name":"Jacob M. Springer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jacob Mitchell Springer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049387196","display_name":"Vaibhav Adlakha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vaibhav Adlakha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102886212","display_name":"Siva Reddy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siva Reddy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031731960","display_name":"Aditi Raghunathan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aditi Raghunathan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084471503","display_name":"Marius Mosbach","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marius Mosbach","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":1.624,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82879087,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"22551","last_page":"22567"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.5539000034332275,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.5539000034332275,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.5087000131607056,"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":0.49309998750686646,"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/computer-science","display_name":"Computer science","score":0.612744927406311},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3560066223144531},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.34779733419418335}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.612744927406311},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3560066223144531},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34779733419418335}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1160","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1160","pdf_url":"https://aclanthology.org/2025.findings-acl.1160.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.1160","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1160","pdf_url":"https://aclanthology.org/2025.findings-acl.1160.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":[],"awards":[{"id":"https://openalex.org/G8051438088","display_name":"Graduate Research Fellowship Program (GRFP)","funder_award_id":"2140739","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887723.pdf","grobid_xml":"https://content.openalex.org/works/W4412887723.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/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2,65],"developing":[3],"general":[4],"purpose":[5],"text":[6],"embedders":[7,123],"has":[8],"been":[9],"driven":[10],"by":[11,48],"training":[12,129],"on":[13,98,109,130],"ever-growing":[14],"corpora":[15],"of":[16,115],"synthetic":[17,23,45,55,72,82,117,131],"LLMgenerated":[18],"data.Nonetheless,":[19],"no":[20],"publicly":[21,42],"available":[22],"dataset":[24],"exists,":[25],"posing":[26],"a":[27],"barrier":[28],"to":[29,62,89,134],"studying":[30],"its":[31],"role":[32],"for":[33,120],"generalization.To":[34],"address":[35],"this":[36],"issue,":[37],"we":[38,67,92],"first":[39],"reproduce":[40],"and":[41,60,86,101,124],"release":[43],"the":[44,96,113,126],"data":[46,56,73,83,102,118,132],"proposed":[47],"Wang":[49],"et":[50],"al.":[51],"(":[52],"2024)":[53],"(Mistral-E5).Our":[54],"is":[57],"high":[58],"quality":[59],"leads":[61,133],"consistent":[63],"improvements":[64],"performance.Next,":[66],"critically":[68],"examine":[69],"where":[70],"exactly":[71],"improves":[74],"model":[75],"generalization.Our":[76],"analysis":[77],"reveals":[78],"that":[79,103,128],"benefits":[80,104],"from":[81],"are":[84],"sparse":[85],"highly":[87],"localized":[88],"individual":[90],"datasets.Moreover,":[91],"observe":[93],"trade-offs":[94],"between":[95],"performance":[97,108],"different":[99],"categories":[100],"one":[105],"task,":[106],"degrades":[107],"another.Our":[110],"findings":[111],"highlight":[112],"limitations":[114],"current":[116],"approaches":[119],"building":[121],"generalpurpose":[122],"challenge":[125],"notion":[127],"more":[135],"robust":[136],"embedding":[137],"models":[138],"across":[139],"tasks.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}