{"id":"https://openalex.org/W7108331775","doi":"https://doi.org/10.1145/3767695.3769491","title":"Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking","display_name":"Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7108331775","doi":"https://doi.org/10.1145/3767695.3769491"},"language":null,"primary_location":{"id":"doi:10.1145/3767695.3769491","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3767695.3769491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yifan Ji","orcid":"https://orcid.org/0000-0001-7594-3132"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Ji","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0001-7594-3132","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhipeng Xu","orcid":"https://orcid.org/0009-0001-3671-5978"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhipeng Xu","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0009-0001-3671-5978","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhenghao Liu","orcid":"https://orcid.org/0000-0003-0083-3224"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenghao Liu","raw_affiliation_strings":["Northeastern University, Shenyang, China","Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0083-3224","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yukun Yan","orcid":"https://orcid.org/0000-0003-2421-7098"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yukun Yan","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2421-7098","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shi Yu","orcid":"https://orcid.org/0000-0001-6335-1076"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi Yu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6335-1076","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yishan Li","orcid":"https://orcid.org/0009-0006-2837-1358"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yishan Li","raw_affiliation_strings":["ModelBest Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-2837-1358","affiliations":[{"raw_affiliation_string":"ModelBest Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiyuan Liu","orcid":"https://orcid.org/0000-0002-7709-2543"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Liu","raw_affiliation_strings":["Northeastern University, Shenyang, China","Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7709-2543","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yu Gu","orcid":"https://orcid.org/0000-0001-7422-6254"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Gu","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0001-7422-6254","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ge Yu","orcid":"https://orcid.org/0000-0002-3171-8889"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Yu","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-3171-8889","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":null,"display_name":"Maosong Sun","orcid":"https://orcid.org/0000-0002-6011-6115"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maosong Sun","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6011-6115","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"292","last_page":"302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.39480000734329224,"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":0.39480000734329224,"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":0.19900000095367432,"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":0.1251000016927719,"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/leverage","display_name":"Leverage (statistics)","score":0.7080000042915344},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6165000200271606},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.47440001368522644},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4706999957561493},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4325999915599823},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.3612000048160553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950000166893005},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7080000042915344},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6165000200271606},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5619000196456909},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.47440001368522644},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4706999957561493},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4325999915599823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39980000257492065},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37619999051094055},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C44083865","wikidata":"https://www.wikidata.org/wiki/Q3853443","display_name":"Mean reciprocal rank","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3767695.3769491","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3767695.3769491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5478543043136597}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2798482016","https://openalex.org/W2912924812","https://openalex.org/W2950681488","https://openalex.org/W2963339397","https://openalex.org/W2963748441","https://openalex.org/W2963957489","https://openalex.org/W2963961878","https://openalex.org/W3021397474","https://openalex.org/W4205103289","https://openalex.org/W4285171517","https://openalex.org/W4384641500","https://openalex.org/W4384644324","https://openalex.org/W4385565351","https://openalex.org/W4385570569","https://openalex.org/W4385570594","https://openalex.org/W4385573358","https://openalex.org/W4385573970","https://openalex.org/W4386488973","https://openalex.org/W4389921502","https://openalex.org/W4391673302","https://openalex.org/W4396843721","https://openalex.org/W4400526199","https://openalex.org/W4402671875","https://openalex.org/W4402672004","https://openalex.org/W4404781354","https://openalex.org/W4404782892","https://openalex.org/W4404783353"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"dense":[1],"retrievers":[2],"increasingly":[3],"leverage":[4],"the":[5,110],"robust":[6],"text":[7],"understanding":[8],"capabilities":[9],"of":[10,90],"Large":[11],"Language":[12],"Models":[13],"(LLMs),":[14],"encoding":[15],"queries":[16],"and":[17,47,108,134,138],"documents":[18],"into":[19,114],"a":[20,35,63,72,78,87,102,115],"shared":[21],"embedding":[22],"space":[23],"for":[24],"effective":[25,41],"retrieval.":[26],"However,":[27],"most":[28,111],"existing":[29,125],"methods":[30,126],"represent":[31],"each":[32],"document":[33,68,84],"with":[34],"single":[36],"embedding,":[37],"which":[38,81],"is":[39],"less":[40],"at":[42,142],"capturing":[43],"its":[44],"multifaceted":[45],"semantics":[46],"thereby":[48],"limits":[49],"matching":[50],"accuracy.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55],"propose":[56],"Deliberate":[57],"Thinking":[58],"based":[59],"Dense":[60],"Retriever":[61],"(Debater),":[62],"novel":[64],"approach":[65],"that":[66,106,121],"enhances":[67],"representations":[69],"by":[70],"incorporating":[71],"step-by-step":[73],"thinking":[74,97],"process.":[75],"Debater":[76,99,122],"introduces":[77],"Chain-of-Deliberation":[79],"mechanism,":[80],"iteratively":[82],"refines":[83],"embeddings":[85],"through":[86],"continuous":[88],"chain":[89],"thought.":[91],"To":[92],"integrate":[93],"information":[94],"from":[95],"various":[96],"steps,":[98],"further":[100],"employs":[101],"Self":[103],"Distillation":[104],"mechanism":[105],"identifies":[107],"fuses":[109],"informative":[112],"steps":[113],"unified":[116],"embedding.":[117],"Experimental":[118],"results":[119],"show":[120],"significantly":[123],"outperforms":[124],"across":[127],"several":[128],"retrieval":[129],"benchmarks,":[130],"demonstrating":[131],"superior":[132],"accuracy":[133],"robustness.":[135],"All":[136],"codes":[137],"datasets":[139],"are":[140],"available":[141],"https://github.com/OpenBMB/DEBATER.":[143]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-03T00:00:00"}