{"id":"https://openalex.org/W7166810378","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1603","title":"Let Retrievers Think Before Action: Thought-Augmented Embedding for Dense Retrieval","display_name":"Let Retrievers Think Before Action: Thought-Augmented Embedding for Dense Retrieval","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166810378","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1603"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1603","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1603","pdf_url":"https://aclanthology.org/2026.findings-acl.1603.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1603.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139822041","display_name":"Ruiran Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruiran Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139777981","display_name":"Wen Xiong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen Xiong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139819600","display_name":"Ze Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ze Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139723260","display_name":"Chaozhuo Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chaozhuo Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139795607","display_name":"Hao Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Liao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139797708","display_name":"Defu Lian","orcid":null},"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/A5139829446","display_name":"Zheng Liu","orcid":null},"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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85985608,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"32032","last_page":"32052"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.36800000071525574,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.36800000071525574,"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/T10028","display_name":"Topic Modeling","score":0.11020000278949738,"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":0.05380000174045563,"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/embedding","display_name":"Embedding","score":0.5130000114440918},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.30160000920295715},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.2773999869823456},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.26019999384880066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6060000061988831},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5130000114440918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4952000081539154},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2808000147342682},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25780001282691956},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2529999911785126},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25099998712539673},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1603","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1603","pdf_url":"https://aclanthology.org/2026.findings-acl.1603.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1603","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1603","pdf_url":"https://aclanthology.org/2026.findings-acl.1603.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166810378.pdf","grobid_xml":"https://content.openalex.org/works/W7166810378.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,27,50],"(LLMs)":[3],"have":[4],"demonstrated":[5],"that":[6,111,146],"explicitly":[7],"performing":[8],"step-by-step":[9],"thinking":[10,91,103],"before":[11,78],"producing":[12],"final":[13],"outputs":[14],"can":[15,147],"substantially":[16],"improve":[17],"performance":[18,190],"on":[19],"complex":[20,68],"tasks,":[21],"as":[22,29],"exemplified":[23],"by":[24,35,161],"recent":[25],"reasoningoriented":[26],"such":[28],"OpenAI":[30],"O1":[31,41,70,199],"and":[32,62,151,166,195],"DeepSeek":[33],"R1.Inspired":[34],"these":[36],"advancements,":[37],"we":[38,84],"propose":[39],"the":[40,193],"Embedder,":[42],"a":[43,121,142,154,180],"novel":[44],"approach":[45],"aiming":[46],"to":[47,54,108],"endow":[48],"retrieval":[49,96,132,168,174],"with":[51,120,131,138],"similar":[52],"capabilities":[53],"address":[55,85,117],"challenges":[56,88],"like":[57],"multi-task":[58],"retrieval,":[59,61],"zero-shot":[60],"tasks":[63,97],"requiring":[64],"intensive":[65],"reasoning":[66],"of":[67,198],"relationships.The":[69],"Embedder":[71,157],"generates":[72],"preliminary":[73],"thoughts":[74,110],"for":[75,101,115],"input":[76],"queries":[77],"document":[79],"retrieval.To":[80],"realize":[81],"this":[82,118,159],"objective,":[83],"two":[86],"fundamental":[87],"in":[89,169],"integrating":[90,135],"mechanisms":[92],"into":[93],"dense":[94,167],"retrieval.First,":[95],"lack":[98],"explicit":[99],"supervision":[100],"intermediate":[102],"processes,":[104],"making":[105],"it":[106],"difficult":[107],"define":[109],"are":[112],"truly":[113],"useful":[114],"retrieval.We":[116],"challenge":[119,160],"data":[122],"synthesis":[123],"framework":[124,145],"following":[125],"an":[126,170],"Exploration-Refinement":[127],"process,":[128],"ensuring":[129],"alignment":[130],"utility.Second,":[133],"effectively":[134],"thought":[136,164],"generation":[137,150,165],"representation":[139],"learning":[140],"requires":[141],"unified":[143],"modeling":[144],"jointly":[148,162],"support":[149],"embedding":[152],"within":[153],"single":[155,181],"model.O1":[156],"addresses":[158],"optimizing":[163],"end-to-end":[171],"manner,":[172],"enhancing":[173],"accuracy":[175],"while":[176],"reducing":[177],"complexity":[178],"through":[179],"deployable":[182],"model.Extensive":[183],"evaluations":[184],"across":[185],"diverse":[186],"datasets":[187],"demonstrate":[188],"significant":[189],"improvements,":[191],"highlighting":[192],"effectiveness":[194],"generalization":[196],"capability":[197],"Embedder.":[200]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}