{"id":"https://openalex.org/W4416250713","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228816","title":"Reinforced Retrieval-Augmented Generation in Large Language Models","display_name":"Reinforced Retrieval-Augmented Generation in Large Language Models","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416250713","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228816"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":"https://openalex.org/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Hsinchu,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092391895","display_name":"Zhi-Xuan Tai","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Zhi-Xuan Tai","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Hsinchu,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7559999823570251,"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":0.7559999823570251,"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":0.07320000231266022,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.017799999564886093,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6933000087738037},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6784999966621399},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.6578999757766724},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5224000215530396},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.5059999823570251},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.48190000653266907}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7533000111579895},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6933000087738037},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6784999966621399},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.6578999757766724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5501000285148621},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5224000215530396},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.5059999823570251},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.48190000653266907},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4778999984264374},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4372999966144562},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42329999804496765},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.41749998927116394},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3837999999523163},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.37720000743865967},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2831000089645386}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2912924812","https://openalex.org/W2951360122","https://openalex.org/W2963339397","https://openalex.org/W3089628124","https://openalex.org/W3117383065","https://openalex.org/W4385482775","https://openalex.org/W4391021740","https://openalex.org/W4392903386","https://openalex.org/W4393147129","https://openalex.org/W4400526126","https://openalex.org/W4401763438","https://openalex.org/W4402352915","https://openalex.org/W4402353656","https://openalex.org/W4402987946","https://openalex.org/W4404752311","https://openalex.org/W4405022026"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,14],"model":[2,65,113],"(LLM)":[3],"has":[4],"been":[5],"recognized":[6],"as":[7],"a":[8,56,62,84,108],"powerful":[9],"learning":[10,69],"machine":[11],"for":[12,126],"natural":[13],"generation.":[15,82,100,128],"However,":[16],"LLM":[17],"likely":[18],"generates":[19],"the":[20,40,50,67,79,91,93,96,103,138,144],"factually":[21],"incorrect":[22],"or":[23],"irrelevant":[24],"responses,":[25],"which":[26],"result":[27],"in":[28,49,98,123,148,155],"an":[29,118],"issue":[30,34],"of":[31,157],"hallucination.":[32],"This":[33,53],"is":[35,75,86,114],"sometimes":[36],"risky":[37],"especially":[38],"when":[39],"application":[41],"domains":[42],"require":[43],"high":[44],"accuracy":[45,106],"with":[46],"safe":[47],"control":[48],"generated":[51],"responses.":[52],"paper":[54],"presents":[55],"reinforced":[57,80,140],"retrieval":[58],"method":[59],"to":[60,77,88,116,120],"build":[61],"trustworthy":[63],"generative":[64],"where":[66],"reinforcement":[68],"based":[70],"on":[71,131],"proximal":[72],"policy":[73],"optimization":[74],"developed":[76],"implement":[78],"retrieval-augmented":[81,141],"Such":[83],"solution":[85],"able":[87],"dynamically":[89],"optimize":[90],"quality,":[92],"consistency":[94],"and":[95,105,133,151],"completion":[97],"content":[99],"By":[101],"balancing":[102],"fluency":[104],"through":[107],"tailored":[109],"reward":[110],"function,":[111],"this":[112],"optimized":[115],"pave":[117],"avenue":[119],"mitigate":[121],"hallucination":[122],"using":[124],"LLMs":[125],"text":[127],"Experimental":[129],"results":[130],"NQ":[132],"TriviaQA":[134],"datasets":[135],"show":[136],"that":[137],"proposed":[139],"generation":[142],"outperforms":[143],"existing":[145],"models":[146],"particularly":[147],"both":[149],"long-form":[150],"short-form":[152],"question-answering":[153],"tasks":[154],"terms":[156],"various":[158],"evaluation":[159],"metrics.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}