{"id":"https://openalex.org/W7165776796","doi":"https://doi.org/10.48550/arxiv.2606.24667","title":"DREAM: Dense Retrieval Embeddings via Autoregressive Modeling","display_name":"DREAM: Dense Retrieval Embeddings via Autoregressive Modeling","publication_year":2026,"publication_date":"2026-06-23","ids":{"openalex":"https://openalex.org/W7165776796","doi":"https://doi.org/10.48550/arxiv.2606.24667"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.24667","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.24667","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.24667","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139224463","display_name":"Yixuan Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Yixuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139265003","display_name":"Yi Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yi","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":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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.6658999919891357,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.6658999919891357,"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/T10028","display_name":"Topic Modeling","score":0.11599999666213989,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03929999843239784,"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/autoregressive-model","display_name":"Autoregressive model","score":0.7815999984741211},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6901999711990356},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.6039999723434448},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.42719998955726624},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.385699987411499},{"id":"https://openalex.org/keywords/dream","display_name":"Dream","score":0.33160001039505005}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7815999984741211},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7099000215530396},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6901999711990356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6187000274658203},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.6039999723434448},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.42719998955726624},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39579999446868896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39149999618530273},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C2781095916","wikidata":"https://www.wikidata.org/wiki/Q36348","display_name":"Dream","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.2992999851703644},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2736000120639801}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.24667","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.24667","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,"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.24667","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.24667","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Dense":[0],"retrieval":[1,173],"embedding":[2,108,179],"models":[3],"are":[4,16,30],"a":[5,49,65,71,106,134,202],"fundamental":[6],"component":[7],"of":[8,48,133],"modern":[9],"retrieval-based":[10],"AI":[11],"systems.":[12],"Most":[13],"dense":[14,58,207],"retrievers":[15,208],"trained":[17],"with":[18],"contrastive":[19],"objectives,":[20],"which":[21,123],"require":[22],"labeled":[23],"positive":[24],"and":[25,33,176],"negative":[26],"document":[27,66,76,147],"pairs":[28],"that":[29,75,92,199],"often":[31],"costly":[32],"difficult":[34],"to":[35,70,86,184],"obtain.":[36],"In":[37],"this":[38,112],"work,":[39],"we":[40,114],"investigate":[41],"whether":[42],"the":[43,79,84,93,100,103,150,153,166],"autoregressive":[44,210],"next-token":[45,94],"prediction":[46,95,158],"objective":[47],"large":[50],"language":[51],"model":[52,194],"(LLM)":[53],"can":[54],"provide":[55],"supervision":[56],"for":[57,83,162,205],"retrieval.":[59],"The":[60,156],"intuition":[61],"is":[62,91,97,105],"simple:":[63],"if":[64],"contains":[67],"information":[68],"relevant":[69],"query,":[72],"conditioning":[73],"on":[74,172],"should":[77],"make":[78],"target":[80,154],"output":[81],"easier":[82],"LLM":[85,151],"predict.":[87],"A":[88],"key":[89],"challenge":[90],"loss":[96,159],"computed":[98],"inside":[99],"LLM,":[101],"while":[102,149],"retriever":[104,163],"separate":[107],"model.":[109],"To":[110],"address":[111],"challenge,":[113],"propose":[115],"DREAM":[116,171,187,200],"(Dense":[117],"Retrieval":[118],"Embeddings":[119],"via":[120],"Autoregressive":[121],"Modeling),":[122],"injects":[124],"retriever-generated":[125],"query-document":[126],"similarity":[127],"scores":[128,140],"into":[129],"selected":[130],"attention":[131,144,167],"heads":[132],"frozen":[135],"LLM.":[136],"During":[137],"training,":[138],"these":[139],"determine":[141],"how":[142],"much":[143],"each":[145],"candidate":[146],"receives":[148],"predicts":[152],"output.":[155],"resulting":[157],"provides":[160,201],"gradients":[161],"training":[164,206],"through":[165,209],"mechanism.":[168],"We":[169],"evaluate":[170],"benchmarks":[174],"BEIR":[175],"RTEB":[177],"using":[178],"backbones":[180],"ranging":[181],"from":[182],"0.5B":[183],"3B":[185],"parameters.":[186],"consistently":[188],"outperforms":[189],"existing":[190],"baselines":[191],"across":[192],"different":[193],"scales.":[195],"These":[196],"results":[197],"demonstrate":[198],"promising":[203],"approach":[204],"modeling.":[211]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-25T00:00:00"}