{"id":"https://openalex.org/W4415315964","doi":"https://doi.org/10.18653/v1/2026.acl-long.2008","title":"LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations","display_name":"LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415315964","doi":"https://doi.org/10.18653/v1/2026.acl-long.2008"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.2008","doi":"https://doi.org/10.18653/v1/2026.acl-long.2008","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2008","pdf_url":"https://aclanthology.org/2026.acl-long.2008.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.acl-long.2008.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017452130","display_name":"Robin Vujanic","orcid":"https://orcid.org/0000-0002-3873-171X","observed_orcids":["https://orcid.org/0000-0002-3873-171X"]},"institutions":[{"id":"https://openalex.org/I4405258135","display_name":"MongoDB (United States)","ror":"https://ror.org/005tgre63","country_code":"US","type":"company","lineage":["https://openalex.org/I4405258135"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robin Vujanic","raw_affiliation_strings":["MongoDB Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MongoDB Research","institution_ids":["https://openalex.org/I4405258135"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061358849","display_name":"Thomas R\u00fcckstie\u00df","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405258135","display_name":"MongoDB (United States)","ror":"https://ror.org/005tgre63","country_code":"US","type":"company","lineage":["https://openalex.org/I4405258135"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas R\u00fcckstie\u00df","raw_affiliation_strings":["MongoDB Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MongoDB Research","institution_ids":["https://openalex.org/I4405258135"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4405258135"],"apc_list":null,"apc_paid":null,"fwci":8.9348,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93102883,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"43362","last_page":"43383"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6596999764442444,"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":0.6596999764442444,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.31200000643730164,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0071000000461936,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/knowledge-distillation","display_name":"knowledge distillation","score":0.996999979019165},{"id":"https://openalex.org/keywords/text-embedding-models","display_name":"text embedding models","score":0.9129999876022339},{"id":"https://openalex.org/keywords/asymmetric-architecture","display_name":"asymmetric architecture","score":0.6499999761581421},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"information retrieval","score":0.6700000166893005},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.5630000233650208},{"id":"https://openalex.org/keywords/representation-robustness","display_name":"representation robustness","score":0.46000000834465027},{"id":"https://openalex.org/keywords/output-quantization","display_name":"output quantization","score":0.890999972820282}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7415000200271606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6941999793052673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49720001220703125},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.487199991941452},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4447999894618988},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4131999909877777},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3756999969482422},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34540000557899475},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C41458344","wikidata":"https://www.wikidata.org/wiki/Q732577","display_name":"Publication","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.2581999897956848},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.2008","doi":"https://doi.org/10.18653/v1/2026.acl-long.2008","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2008","pdf_url":"https://aclanthology.org/2026.acl-long.2008.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.12539","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2509.12539","pdf_url":"https://arxiv.org/pdf/2509.12539","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.12539","doi":"https://doi.org/10.48550/arxiv.2509.12539","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.12539","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.2008","doi":"https://doi.org/10.18653/v1/2026.acl-long.2008","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2008","pdf_url":"https://aclanthology.org/2026.acl-long.2008.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415315964.pdf","grobid_xml":"https://content.openalex.org/works/W4415315964.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4318719671","https://openalex.org/W2989716187","https://openalex.org/W4405901329","https://openalex.org/W7168344481","https://openalex.org/W4393399864","https://openalex.org/W7212648078","https://openalex.org/W7154502720","https://openalex.org/W7130359175","https://openalex.org/W4416036928","https://openalex.org/W4392384310"],"abstract_inverted_index":{"We":[0],"present":[1,65],"LEAF":[2],"(\"Lightweight":[3],"Embedding":[4],"Alignment":[5],"Framework\"),":[6],"a":[7,84,100,143,196],"knowledge":[8],"distillation":[9],"framework":[10,80,187],"for":[11,73,112,155,185],"text":[12],"embedding":[13],"models.A":[14],"key":[15],"distinguishing":[16],"feature":[17],"is":[18,124,160],"that":[19,50],"our":[20,79,186,191],"distilled":[21],"leaf":[22,46,51],"models":[23,52,113,156,192],"are":[24,35,64,188],"compatible":[25],"with":[26,37],"their":[27],"teacher,":[28],"enabling":[29],"flexible":[30],"asymmetric":[31],"architectures":[32],"where":[33],"documents":[34],"encoded":[36],"the":[38,67,76,109,137,149],"larger":[39],"teacher":[40,68],"model,":[41,69],"while":[42],"queries":[43],"use":[44],"smaller":[45],"models.We":[47],"also":[48,141],"show":[49],"automatically":[53],"inherit":[54],"MRL":[55],"and":[56,171,181],"robustness":[57],"to":[58,128,162],"output":[59],"quantization":[60],"whenever":[61],"these":[62],"properties":[63],"in":[66],"without":[70],"explicitly":[71],"training":[72,172,182],"them.To":[74],"demonstrate":[75,131],"effectiveness":[77],"of":[78,114,157],"we":[81],"publish":[82],"leaf-ir,":[83],"23M":[85],"parameters":[86],"information":[87,129],"retrieval":[88,121],"oriented":[89],"model":[90],"focusing":[91],"on":[92,104,108,148],"English":[93],"texts":[94],"that,":[95],"besides":[96],"being":[97],"teacher-compatible,":[98],"sets":[99,142],"new":[101,144],"state-of-the-art":[102],"(SOTA)":[103],"BEIR,":[105],"ranking":[106],"no.1":[107,147],"public":[110,150],"leaderboard":[111,154],"its":[115,120,132,158],"size.Asymmetric":[116],"mode":[117],"further":[118],"increases":[119],"performance.Our":[122],"scheme":[123],"however":[125],"not":[126],"restricted":[127],"retrieval.We":[130],"wider":[133],"applicability":[134],"by":[135],"synthesizing":[136],"multi-task":[138],"leaf-mt":[139],"model.This":[140],"SOTA,":[145],"achieving":[146],"MTEB":[151],"v2":[152],"(English)":[153],"size.LEAF":[159],"applicable":[161],"black-box":[163],"models,":[164],"requires":[165],"no":[166],"judgments":[167],"nor":[168],"hard":[169],"negatives,":[170],"can":[173],"be":[174],"conducted":[175],"using":[176],"small":[177],"batch":[178],"sizes.Thus,":[179],"dataset":[180],"infrastructure":[183],"requirements":[184],"modest.We":[189],"make":[190],"publicly":[193],"available":[194],"under":[195],"permissive":[197],"Apache":[198],"2.0":[199],"license.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2025-10-18T00:00:00"}