{"id":"https://openalex.org/W4387635415","doi":"https://doi.org/10.48550/arxiv.2310.08232","title":"Language Models are Universal Embedders","display_name":"Language Models are Universal Embedders","publication_year":2023,"publication_date":"2023-10-12","ids":{"openalex":"https://openalex.org/W4387635415","doi":"https://doi.org/10.48550/arxiv.2310.08232"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.08232","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.08232","pdf_url":"https://arxiv.org/pdf/2310.08232","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.08232","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100327428","display_name":"Xin Zhang","orcid":"https://orcid.org/0000-0002-2550-3056"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Xin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076041866","display_name":"Zehan Li","orcid":"https://orcid.org/0000-0002-4996-8480"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zehan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103114439","display_name":"Yanzhao Zhang","orcid":"https://orcid.org/0000-0003-2894-4727"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yanzhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049484480","display_name":"Dingkun Long","orcid":"https://orcid.org/0000-0001-6570-9406"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long, Dingkun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005535444","display_name":"Pengjun Xie","orcid":"https://orcid.org/0009-0004-8412-359X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Pengjun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004953265","display_name":"Meishan Zhang","orcid":"https://orcid.org/0000-0001-6335-1340"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Meishan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5012727269","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0003-1643-5271"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Min","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100327428"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.9991000294685364,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9975000023841858,"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":0.9789999723434448,"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":0.8766776323318481},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6840069890022278},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5280787944793701},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5123533010482788},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5000097751617432},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.47363394498825073},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.46229785680770874},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4483095109462738},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.43751251697540283},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.37846246361732483},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36057525873184204},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09275171160697937}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8766776323318481},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6840069890022278},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5280787944793701},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5123533010482788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5000097751617432},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.47363394498825073},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46229785680770874},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4483095109462738},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.43751251697540283},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.37846246361732483},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36057525873184204},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09275171160697937},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.08232","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.08232","pdf_url":"https://arxiv.org/pdf/2310.08232","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2310.08232","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.08232","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.08232","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.08232","pdf_url":"https://arxiv.org/pdf/2310.08232","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387635415.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W3098382480","https://openalex.org/W4287598411","https://openalex.org/W3094871513","https://openalex.org/W3100913109","https://openalex.org/W3198458223","https://openalex.org/W3126642501"],"abstract_inverted_index":{"In":[0,62],"the":[1,65,142],"large":[2,69],"language":[3,70],"model":[4,54,103],"(LLM)":[5],"revolution,":[6],"embedding":[7,53],"is":[8,47,104,125],"a":[9,51,76,93],"key":[10],"component":[11],"of":[12,144],"various":[13],"systems,":[14],"such":[15,29],"as":[16,75],"retrieving":[17],"knowledge":[18],"or":[19,23,37],"memories":[20],"for":[21,59,88,120],"LLMs":[22],"building":[24],"content":[25],"moderation":[26],"filters.":[27],"As":[28],"cases":[30],"span":[31],"from":[32,40],"English":[33],"to":[34,42,49,116],"other":[35],"natural":[36],"programming":[38],"languages,":[39],"retrieval":[41],"classification":[43],"and":[44,91,112,118,132],"beyond,":[45],"it":[46],"advantageous":[48],"build":[50],"unified":[52],"rather":[55],"than":[56],"dedicated":[57],"ones":[58],"each":[60],"scenario.":[61],"this":[63,138],"context,":[64],"pre-trained":[66],"multilingual":[67],"decoder-only":[68],"models,":[71],"e.g.,":[72],"BLOOM,":[73],"emerge":[74],"viable":[77],"backbone":[78],"option.":[79],"To":[80],"assess":[81],"their":[82],"potential,":[83],"we":[84],"propose":[85],"straightforward":[86],"strategies":[87],"constructing":[89],"embedders":[90],"introduce":[92],"universal":[94,148],"evaluation":[95],"benchmark.":[96],"Experimental":[97],"results":[98],"show":[99],"that":[100,137],"our":[101],"trained":[102],"proficient":[105],"at":[106],"generating":[107],"good":[108],"embeddings":[109],"across":[110],"languages":[111,117],"tasks,":[113],"even":[114],"extending":[115],"tasks":[119],"which":[121],"no":[122],"finetuning/pretraining":[123],"data":[124],"available.":[126],"We":[127,135],"also":[128],"present":[129],"detailed":[130],"analyses":[131],"additional":[133],"evaluations.":[134],"hope":[136],"work":[139],"could":[140],"encourage":[141],"development":[143],"more":[145],"robust":[146],"open-source":[147],"embedders.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}