{"id":"https://openalex.org/W4380136635","doi":"https://doi.org/10.48550/arxiv.2306.05212","title":"RETA-LLM: A Retrieval-Augmented Large Language Model Toolkit","display_name":"RETA-LLM: A Retrieval-Augmented Large Language Model Toolkit","publication_year":2023,"publication_date":"2023-06-08","ids":{"openalex":"https://openalex.org/W4380136635","doi":"https://doi.org/10.48550/arxiv.2306.05212"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2306.05212","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.05212","pdf_url":"https://arxiv.org/pdf/2306.05212","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2306.05212","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050522242","display_name":"Jiongnan Liu","orcid":"https://orcid.org/0000-0002-3946-9178","observed_orcids":["https://orcid.org/0000-0002-3946-9178"]},"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":"Liu, Jiongnan","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113123612","display_name":"Jiajie Jin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin, Jiajie","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380108","display_name":"Zihan Wang","orcid":"https://orcid.org/0009-0009-0604-2416","observed_orcids":["https://orcid.org/0009-0009-0604-2416","https://orcid.org/0000-0003-1056-6326"]},"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":"Wang, Zihan","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113852558","display_name":"Jiehan Cheng","orcid":null,"observed_orcids":[]},"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":"Cheng, Jiehan","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010558184","display_name":"Zhicheng Dou","orcid":"https://orcid.org/0000-0002-9781-948X","observed_orcids":["https://orcid.org/0000-0002-9781-948X"]},"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":"Dou, Zhicheng","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025631695","display_name":"Ji-Rong Wen","orcid":"https://orcid.org/0000-0002-9777-9676","observed_orcids":["https://orcid.org/0000-0002-9777-9676"]},"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":"Wen, Ji-Rong","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]}],"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":true,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5009999871253967,"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":0.5009999871253967,"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":0.48579999804496765,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.00430000014603138,"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/information-retrieval","display_name":"information retrieval","score":0.6259999871253967},{"id":"https://openalex.org/keywords/hallucination-mitigation","display_name":"hallucination mitigation","score":0.796999990940094},{"id":"https://openalex.org/keywords/fact-checking","display_name":"fact-checking","score":0.6869999766349792},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"document retrieval","score":0.8600000143051147},{"id":"https://openalex.org/keywords/answer-generation","display_name":"answer generation","score":0.9890000224113464},{"id":"https://openalex.org/keywords/external-knowledge-integration","display_name":"external knowledge integration","score":0.6230000257492065}],"concepts":[{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.6914688348770142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5761400461196899},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5732781291007996},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.469424307346344},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.434722363948822},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.38299092650413513},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11618906259536743},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2306.05212","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.05212","pdf_url":"https://arxiv.org/pdf/2306.05212","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,"listed_in":[],"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.2306.05212","doi":"https://doi.org/10.48550/arxiv.2306.05212","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2306.05212","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2306.05212","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.05212","pdf_url":"https://arxiv.org/pdf/2306.05212","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,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4380136635.pdf","grobid_xml":"https://content.openalex.org/works/W4380136635.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416139362","https://openalex.org/W4322718421","https://openalex.org/W4403487546","https://openalex.org/W4402670192","https://openalex.org/W4412945122","https://openalex.org/W4404346313","https://openalex.org/W4412183874","https://openalex.org/W4403785829","https://openalex.org/W4402684013","https://openalex.org/W4416251204"],"abstract_inverted_index":{"Although":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"have":[5,14],"demonstrated":[6],"extraordinary":[7],"capabilities":[8],"in":[9,53,96,101],"many":[10],"domains,":[11],"they":[12],"still":[13],"a":[15,115,123],"tendency":[16],"to":[17,23,55,59,126,148],"hallucinate":[18],"and":[19,104,129,155,166],"generate":[20,49],"fictitious":[21],"responses":[22],"user":[24,56],"requests.":[25],"This":[26],"problem":[27],"can":[28,48,80],"be":[29,86],"alleviated":[30],"by":[31,64,74,88],"augmenting":[32],"LLMs":[33,47,79],"with":[34,138],"information":[35],"retrieval":[36],"(IR)":[37],"systems":[38,66,154],"(also":[39],"known":[40],"as":[41,70],"retrieval-augmented":[42,78,109,140],"LLMs).":[43],"Applying":[44],"this":[45,102],"strategy,":[46],"more":[50,145],"factual":[51],"texts":[52],"response":[54],"input":[57],"according":[58],"the":[60,92,106],"relevant":[61],"content":[62],"retrieved":[63],"IR":[65,153],"from":[67],"external":[68,76],"corpora":[69],"references.":[71],"In":[72,119],"addition,":[73],"incorporating":[75],"knowledge,":[77],"answer":[81,164],"in-domain":[82,134],"questions":[83],"that":[84],"cannot":[85],"answered":[87],"solely":[89],"relying":[90],"on":[91],"world":[93],"knowledge":[94],"stored":[95],"parameters.":[97],"To":[98],"support":[99,149],"research":[100],"area":[103],"facilitate":[105],"development":[107],"of":[108],"LLM":[110,117,141],"systems,":[111,142],"we":[112,121],"develop":[113],"RETA-LLM,":[114,120],"{RET}reival-{A}ugmented":[116],"toolkit.":[118],"create":[122],"complete":[124],"pipeline":[125],"help":[127],"researchers":[128],"users":[130],"build":[131],"their":[132],"customized":[133],"LLM-based":[135],"systems.":[136],"Compared":[137],"previous":[139],"RETA-LLM":[143],"provides":[144],"plug-and-play":[146],"modules":[147],"better":[150],"interaction":[151],"between":[152],"LLMs,":[156],"including":[157],"{request":[158],"rewriting,":[159],"document":[160],"retrieval,":[161],"passage":[162],"extraction,":[163],"generation,":[165],"fact":[167],"checking}":[168],"modules.":[169],"Our":[170],"toolkit":[171],"is":[172],"publicly":[173],"available":[174],"at":[175],"https://github.com/RUC-GSAI/YuLan-IR/tree/main/RETA-LLM.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2023-06-10T00:00:00"}