{"id":"https://openalex.org/W7133320300","doi":"https://doi.org/10.48550/arxiv.2603.01425","title":"LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval","display_name":"LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval","publication_year":2026,"publication_date":"2026-03-02","ids":{"openalex":"https://openalex.org/W7133320300","doi":"https://doi.org/10.48550/arxiv.2603.01425"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.01425","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01425","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":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.2603.01425","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127925168","display_name":"Jiajie Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Jiajie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127920688","display_name":"Yanzhao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yanzhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127885990","display_name":"Mingxin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Mingxin","raw_affiliation_strings":[],"raw_orcid":null,"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":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128018390","display_name":"Pengjun Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Pengjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127951444","display_name":"Yutao Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Yutao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127990961","display_name":"Zhicheng Dou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dou, Zhicheng","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/T10028","display_name":"Topic Modeling","score":0.45179998874664307,"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":0.45179998874664307,"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":0.27239999175071716,"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"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.06710000336170197,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6708999872207642},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.4383000135421753},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.42329999804496765},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.385699987411499},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.3785000145435333},{"id":"https://openalex.org/keywords/deductive-reasoning","display_name":"Deductive reasoning","score":0.36390000581741333},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.36090001463890076},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3425000011920929},{"id":"https://openalex.org/keywords/causal-reasoning","display_name":"Causal reasoning","score":0.3407000005245209}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6708999872207642},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6668999791145325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5378000140190125},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.4383000135421753},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.42329999804496765},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.385699987411499},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3725000023841858},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.3407000005245209},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3109000027179718},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.25769999623298645},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.01425","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01425","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.01425","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01425","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7733745574951172}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"LLMs":[0,20],"have":[1],"fundamentally":[2],"transformed":[3],"dense":[4,80,227],"retrieval,":[5],"upgrading":[6],"backbones":[7,187],"from":[8],"discriminative":[9],"encoders":[10],"to":[11,49,158],"generative":[12],"architectures.":[13],"However,":[14,56],"a":[15,67,84,90,104,121,131],"critical":[16],"disconnect":[17],"remains:":[18],"while":[19],"possess":[21],"strong":[22],"reasoning":[23,38,74,101,152,215],"capabilities,":[24],"current":[25],"retrievers":[26],"predominantly":[27],"utilize":[28],"them":[29],"as":[30],"static":[31],"encoders,":[32],"leaving":[33],"their":[34],"potential":[35],"for":[36,205],"complex":[37],"unexplored.":[39],"To":[40,112],"address":[41],"this,":[42],"existing":[43],"approaches":[44],"typically":[45],"adopt":[46],"rewrite-then-retrieve":[47],"pipelines":[48,220],"generate":[50],"explicit":[51,73,151,218],"CoT":[52,219],"rationales":[53],"before":[54],"retrieval.":[55],"this":[57,62],"incurs":[58],"prohibitive":[59],"latency.":[60],"In":[61],"paper,":[63],"we":[64,119,129],"propose":[65],"LaSER,":[66],"novel":[68],"self-distillation":[69],"framework":[70,202],"that":[71,97,107,135,177,198],"internalizes":[72],"into":[75],"the":[76,114,137,142,146,150,156,192,214,222],"latent":[77,110,139,143,208],"space":[78],"of":[79,141,149,194,217,225],"retrievers.":[81,228],"Operating":[82],"on":[83,169],"shared":[85],"LLM":[86],"backbone,":[87],"LaSER":[88,178],"introduces":[89],"dual-view":[91],"training":[92],"mechanism:":[93],"an":[94],"Explicit":[95],"view":[96,106],"explicitly":[98],"encodes":[99],"ground-truth":[100],"paths,":[102],"and":[103,161,172,188],"Latent":[105],"performs":[108],"implicit":[109],"thinking.":[111,209],"bridge":[113],"gap":[115],"between":[116],"these":[117],"views,":[118],"design":[120],"multi-grained":[122],"alignment":[123,133],"strategy.":[124],"Beyond":[125],"standard":[126,226],"output":[127],"alignment,":[128],"introduce":[130],"trajectory":[132],"mechanism":[134],"synchronizes":[136],"intermediate":[138],"states":[140],"path":[144],"with":[145,221],"semantic":[147],"progression":[148],"segments.":[153],"This":[154],"allows":[155],"retriever":[157],"think":[159],"silently":[160],"effectively":[162],"without":[163],"autoregressive":[164],"text":[165],"generation.":[166],"Extensive":[167],"experiments":[168],"both":[170],"in-domain":[171],"out-of-domain":[173],"reasoning-intensive":[174],"benchmarks":[175],"demonstrate":[176],"significantly":[179],"outperforms":[180],"state-of-the-art":[181],"baselines.":[182],"Furthermore,":[183],"analyses":[184],"across":[185],"diverse":[186],"model":[189],"scales":[190],"validate":[191],"robustness":[193],"our":[195,199],"approach,":[196],"confirming":[197],"unified":[200],"learning":[201],"is":[203],"essential":[204],"eliciting":[206],"effective":[207],"Our":[210],"method":[211],"successfully":[212],"combines":[213],"depth":[216],"inference":[223],"efficiency":[224]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-04T00:00:00"}