{"id":"https://openalex.org/W7135027088","doi":"https://doi.org/10.48550/arxiv.2603.10913","title":"LLM2Vec-Gen: Generative Embeddings from Large Language Models","display_name":"LLM2Vec-Gen: Generative Embeddings from Large Language Models","publication_year":2026,"publication_date":"2026-03-11","ids":{"openalex":"https://openalex.org/W7135027088","doi":"https://doi.org/10.48550/arxiv.2603.10913"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.10913","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10913","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.10913","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063732194","display_name":"Parishad BehnamGhader","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"BehnamGhader, Parishad","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":"Adlakha, Vaibhav","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011479082","display_name":"Fabian David Schmidt","orcid":"https://orcid.org/0009-0007-9841-2941"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schmidt, Fabian David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039831068","display_name":"Nicolas Chapados","orcid":"https://orcid.org/0000-0003-0249-7607"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chapados, Nicolas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084471503","display_name":"Marius Mosbach","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mosbach, Marius","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108816545","display_name":"Siva Reddy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reddy, Siva","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5063732194"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":0.7501999735832214,"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":0.7501999735832214,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.1551000028848648,"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":0.01119999960064888,"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/embedding","display_name":"Embedding","score":0.8844000101089478},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5758000016212463},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5738999843597412},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5663999915122986},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.490200012922287},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.40790000557899475},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4020000100135803},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.38510000705718994},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.37779998779296875}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8844000101089478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7763000130653381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6381000280380249},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5828999876976013},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5758000016212463},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5738999843597412},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5663999915122986},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.490200012922287},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.38510000705718994},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3711000084877014},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25940001010894775},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.10913","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10913","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.10913","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10913","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7982497811317444}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fine-tuning":[0],"LLM-based":[1],"text":[2,153],"embedders":[3],"via":[4],"contrastive":[5],"learning":[6,38],"maps":[7],"inputs":[8],"and":[9,54,72,82,131],"outputs":[10],"into":[11,62,152],"a":[12,24,63,73],"new":[13],"representational":[14],"space,":[15],"discarding":[16],"the":[17,33,41,52,58,77,94,104,109,112,141],"LLM's":[18,34,59,113],"output":[19,35],"semantics.":[20],"We":[21],"propose":[22],"LLM2Vec-Gen,":[23],"self-supervised":[25,91],"alternative":[26],"that":[27],"instead":[28],"produces":[29],"embeddings":[30,110,143],"directly":[31],"in":[32,127],"space":[36],"by":[37,67,101],"to":[39,51,56,124,134,154],"represent":[40],"model's":[42],"potential":[43],"response.":[44],"Specifically,":[45],"trainable":[46],"special":[47],"tokens":[48],"are":[49,144],"appended":[50],"input":[53],"optimized":[55],"compress":[57],"own":[60],"response":[61],"fixed-length":[64],"embedding,":[65],"guided":[66],"an":[68],"unsupervised":[69,105],"embedding":[70,106],"teacher":[71],"reconstruction":[74],"objective.":[75],"Crucially,":[76],"LLM":[78],"backbone":[79],"remains":[80],"frozen":[81],"training":[83],"requires":[84],"only":[85],"unlabeled":[86],"queries.":[87],"LLM2Vec-Gen":[88],"achieves":[89],"state-of-the-art":[90],"performance":[92],"on":[93,137],"Massive":[95],"Text":[96],"Embedding":[97],"Benchmark":[98],"(MTEB),":[99],"improving":[100],"8.8%":[102],"over":[103],"teacher.":[107],"Since":[108],"preserve":[111],"response-space":[114],"semantics,":[115],"they":[116,147],"inherit":[117],"capabilities":[118],"such":[119],"as":[120],"safety":[121],"alignment":[122],"(up":[123,133],"22.6%":[125],"reduction":[126],"harmful":[128],"content":[129],"retrieval)":[130],"reasoning":[132],"35.6%":[135],"improvement":[136],"reasoning-intensive":[138],"retrieval).":[139],"Finally,":[140],"learned":[142],"also":[145],"interpretable:":[146],"can":[148],"be":[149],"decoded":[150],"back":[151],"reveal":[155],"their":[156],"semantic":[157],"content.":[158]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-03-13T00:00:00"}