{"id":"https://openalex.org/W4416384301","doi":"https://doi.org/10.18653/v1/2026.acl-long.54","title":"ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval","display_name":"ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416384301","doi":"https://doi.org/10.18653/v1/2026.acl-long.54"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.54","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.54","pdf_url":"https://aclanthology.org/2026.acl-long.54.pdf","source":null,"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"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.54.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058732371","display_name":"Jianlyu Chen","orcid":"https://orcid.org/0009-0008-3367-1149"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianlyu Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111222178","display_name":"Junwei Lan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junwei Lan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032664897","display_name":"Chaofan Li","orcid":"https://orcid.org/0000-0001-7554-6049"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chaofan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085254654","display_name":"Defu Lian","orcid":"https://orcid.org/0000-0002-3507-9607"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Defu Lian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112121955","display_name":"Zheng Liu","orcid":"https://orcid.org/0009-0005-3946-7067"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng Liu","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":21.2894,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96725716,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1203","last_page":"1221"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.35100001096725464,"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":0.35100001096725464,"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":0.28630000352859497,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.16990000009536743,"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":0.7067000269889832},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.670799970626831},{"id":"https://openalex.org/keywords/triviality","display_name":"Triviality","score":0.5304999947547913},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5238999724388123},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.4027000069618225},{"id":"https://openalex.org/keywords/data-retrieval","display_name":"Data retrieval","score":0.37209999561309814},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.33550000190734863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8069000244140625},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7067000269889832},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.670799970626831},{"id":"https://openalex.org/C2778795013","wikidata":"https://www.wikidata.org/wiki/Q945127","display_name":"Triviality","level":2,"score":0.5304999947547913},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5238999724388123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5234000086784363},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4523000121116638},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.4027000069618225},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37279999256134033},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29499998688697815},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.54","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.54","pdf_url":"https://aclanthology.org/2026.acl-long.54.pdf","source":null,"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:2510.08252","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.08252","pdf_url":"https://arxiv.org/pdf/2510.08252","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.08252","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.08252","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:10.18653/v1/2026.acl-long.54","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.54","pdf_url":"https://aclanthology.org/2026.acl-long.54.pdf","source":null,"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":[],"awards":[{"id":"https://openalex.org/G5499064096","display_name":null,"funder_award_id":"U24A20253","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416384301.pdf","grobid_xml":"https://content.openalex.org/works/W4416384301.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,140],"paper,":[2],"we":[3,22,48,81],"introduce":[4],"ReasonEmbed,":[5],"a":[6,25,51,104],"novel":[7],"text":[8,122],"embedding":[9,123],"model":[10,69,102],"developed":[11],"for":[12],"reasoning-intensive":[13,97],"document":[14],"retrieval.Our":[15],"work":[16],"includes":[17],"three":[18],"key":[19],"technical":[20],"contributions.First,":[21],"propose":[23],"ReMixer,":[24],"new":[26],"data":[27],"synthesis":[28],"method":[29],"that":[30,55],"overcomes":[31],"the":[32,68,73,111,136],"triviality":[33],"problem":[34],"prevalent":[35],"in":[36,131,139],"previous":[37],"synthetic":[38],"datasets,":[39],"enabling":[40],"large-scale":[41],"production":[42],"of":[43,87,91,108],"82K":[44],"highquality":[45],"training":[46,58],"samples.Second,":[47],"design":[49],"Redapter,":[50],"self-adaptive":[52],"learning":[53],"algorithm":[54],"dynamically":[56],"adjusts":[57],"each":[59],"sample's":[60],"weight":[61],"based":[62],"on":[63,96,110],"its":[64],"reasoning":[65],"intensity.This":[66],"allows":[67],"to":[70,133],"effectively":[71],"capture":[72],"complex":[74],"semantic":[75],"relationships":[76],"between":[77],"queries":[78],"and":[79],"documents.Third,":[80],"implement":[82],"Rea-sonEmbed":[83],"across":[84],"multiple":[85],"backbones":[86],"varying":[88],"sizes,":[89],"all":[90],"which":[92,118],"achieve":[93],"superior":[94],"performance":[95],"retrieval":[98],"tasks.Notably,":[99],"our":[100,128],"ReasonEmbed-Qwen3-8B":[101],"offers":[103],"record-high":[105],"nDCG@10":[106],"score":[107],"38.1":[109],"BRIGHT":[112],"benchmark":[113],"(SU":[114],"et":[115],"al.,":[116],"2025),":[117],"significantly":[119],"outperforms":[120],"existing":[121],"models.We":[124],"will":[125],"fully":[126],"open-source":[127],"created":[129],"resources":[130],"ReasonEmbed":[132],"push":[134],"forward":[135],"research":[137],"advancement":[138],"field":[141],"1":[142],".":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-11T00:00:00"}