{"id":"https://openalex.org/W7117740016","doi":"https://doi.org/10.1109/tkde.2025.3649907","title":"Empowering Large Language Models to Set Up Knowledge Retrieval Indexing via Self-Learning","display_name":"Empowering Large Language Models to Set Up Knowledge Retrieval Indexing via Self-Learning","publication_year":2025,"publication_date":"2025-12-31","ids":{"openalex":"https://openalex.org/W7117740016","doi":"https://doi.org/10.1109/tkde.2025.3649907"},"language":null,"primary_location":{"id":"doi:10.1109/tkde.2025.3649907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2025.3649907","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","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":"https://openalex.org/A5101323135","display_name":"Simin Niu","orcid":"https://orcid.org/0009-0009-1862-8959"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Simin Niu","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-1862-8959","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101678387","display_name":"Mengwei Wang","orcid":"https://orcid.org/0009-0005-9931-9912"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengwei Wang","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121673855","display_name":"Xun Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Liang","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiyu Li","orcid":"https://orcid.org/0009-0008-3196-7739"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyu Li","raw_affiliation_strings":["Institute for Advanced Algorithms Research, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-3196-7739","affiliations":[{"raw_affiliation_string":"Institute for Advanced Algorithms Research, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101600324","display_name":"Sensen Zhang","orcid":"https://orcid.org/0000-0002-0449-4699"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sensen Zhang","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0449-4699","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102747119","display_name":"Shichao Song","orcid":"https://orcid.org/0009-0005-4575-9592"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shichao Song","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-4575-9592","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121658332","display_name":"Hanyu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanyu Wang","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121639219","display_name":"Jiawei Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Yang","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114134120","display_name":"Feiyu Xiong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feiyu Xiong","raw_affiliation_strings":["Institute for Advanced Algorithms Research, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Advanced Algorithms Research, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058308218","display_name":"Chenyang Xi","orcid":"https://orcid.org/0000-0002-8211-2430"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenyang Xi","raw_affiliation_strings":["Institute for Advanced Algorithms Research, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Advanced Algorithms Research, Shanghai, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78481349,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"3","first_page":"1710","last_page":"1724"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6617000102996826,"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":0.6617000102996826,"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":0.07249999791383743,"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":0.06620000302791595,"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/search-engine-indexing","display_name":"Search engine indexing","score":0.9132999777793884},{"id":"https://openalex.org/keywords/knowledge-retrieval","display_name":"Knowledge retrieval","score":0.5133000016212463},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.45840001106262207},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45719999074935913},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.41029998660087585},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.39480000734329224},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.37790000438690186},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.35339999198913574}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.9132999777793884},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8324000239372253},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.550000011920929},{"id":"https://openalex.org/C2780613888","wikidata":"https://www.wikidata.org/wiki/Q6423394","display_name":"Knowledge retrieval","level":3,"score":0.5133000016212463},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.45840001106262207},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31679999828338623},{"id":"https://openalex.org/C2779810430","wikidata":"https://www.wikidata.org/wiki/Q1929761","display_name":"Knowledge organization","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3061000108718872},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C2778330532","wikidata":"https://www.wikidata.org/wiki/Q4826577","display_name":"Automatic indexing","level":3,"score":0.2976999878883362},{"id":"https://openalex.org/C84685590","wikidata":"https://www.wikidata.org/wiki/Q1540472","display_name":"Knowledge engineering","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.29409998655319214},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C56289545","wikidata":"https://www.wikidata.org/wiki/Q6423376","display_name":"Knowledge integration","level":3,"score":0.2791000008583069},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2025.3649907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2025.3649907","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7004291415214539,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2102625004","https://openalex.org/W2122111042","https://openalex.org/W2970641574","https://openalex.org/W3102378333","https://openalex.org/W4252076394","https://openalex.org/W4385570161","https://openalex.org/W4390692489","https://openalex.org/W4393152682","https://openalex.org/W4400460572","https://openalex.org/W4401042753","https://openalex.org/W4402567773","https://openalex.org/W4402670862","https://openalex.org/W4402671633","https://openalex.org/W4402671983","https://openalex.org/W4403560390","https://openalex.org/W4404783040","https://openalex.org/W4412158322","https://openalex.org/W4412886636"],"related_works":[],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1],"(RAG)":[2],"provides":[3],"an":[4],"efficient":[5],"solution":[6],"for":[7],"expanding":[8],"the":[9,18,55,96,102,107,146,152,157,171,201,236],"knowledge":[10,62,89,108,142,148,153,166,172,179,190],"boundaries":[11],"of":[12,58,109,227],"large":[13],"language":[14],"models":[15],"(LLMs),":[16],"where":[17],"indexing":[19,34,42,63,90,97,154,205],"serves":[20],"as":[21,151],"a":[22,38,85,114,177],"compass":[23],"to":[24,45,105,181],"guide":[25],"LLMs":[26,104],"in":[27,211],"locating":[28],"query-relevant":[29,189],"external":[30],"knowledge.":[31,60,122],"Nevertheless,":[32],"current":[33],"methods":[35],"commonly":[36],"encounter":[37],"critical":[39],"challenge:":[40],"native":[41],"is":[43,70,242],"convenient":[44],"construct,":[46],"but":[47,68],"it":[48,69],"usually":[49],"disrupts":[50],"contextual":[51,66],"associations":[52],"and":[53,87,116,167,187,206,216,231,234],"constrains":[54],"expressive":[56],"capacity":[57],"rich":[59],"Conversely,":[61],"can":[64,155],"structure":[65],"knowledge,":[67],"often":[71],"based":[72],"on":[73,164],"preset":[74,165],"schemas":[75],"that":[76,196],"limit":[77],"its":[78],"generalizability.":[79],"To":[80],"address":[81],"it,":[82],"we":[83,100,175],"propose":[84],"universal":[86],"flexible":[88],"called":[91],"pseudo-graph":[92],"(PG)":[93],"indexing.":[94],"During":[95,170],"construction":[98],"phase,":[99,174],"use":[101],"advanced":[103],"transform":[106],"each":[110],"raw":[111],"text":[112],"into":[113],"concise":[115],"structured":[117],"mind":[118,125],"map,":[119],"organizing":[120],"intra-document":[121],"Subsequently,":[123],"independent":[124],"maps":[126],"are":[127],"linked":[128],"by":[129],"associating":[130],"highly":[131],"relevant":[132,198],"topics":[133],"or":[134],"consistent":[135],"facts":[136],"across":[137],"documents,":[138],"thereby":[139],"establishing":[140],"inter-document":[141],"connections.":[143],"Eventually,":[144],"using":[145],"resulting":[147],"network":[149],"PG":[150,178,202,204],"circumvent":[156],"challenges":[158],"associated":[159],"with":[160],"schema":[161],"design":[162],"reliant":[163],"relationship":[168],"types.":[169],"retrieval":[173],"develop":[176],"retriever":[180,207],"mimic":[182],"human":[183],"note-reviewing,":[184],"adaptively":[185],"navigating":[186],"recalling":[188],"from":[191,200],"PG.":[192],"Experimental":[193],"results":[194],"demonstrate":[195],"retrieving":[197],"pseudo-subgraphs":[199],"via":[203],"significantly":[208],"improves":[209],"performance":[210],"fact-based":[212],"Q&A,":[213],"hallucination":[214],"correction,":[215],"two":[217],"multi-document":[218],"Q&A":[219],"tasks,":[220],"achieving":[221],"<inline-formula":[222],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[223,246],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[224],"notation=\"LaTeX\">$F1_{QE}$</tex-math></inline-formula>":[225],"improvements":[226],"15.85%,":[228],"8.12%,":[229],"3.34%,":[230],"5.73%,":[232],"respectively,":[233],"outperforming":[235],"state-of-the-art":[237],"baseline":[238],"KGP-LLaMA.":[239],"Our":[240],"code":[241],"available":[243],"at:":[244],"<uri":[245],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/IAAR-Shanghai/PGRAG.</uri>":[247]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-31T00:00:00"}