{"id":"https://openalex.org/W4404181042","doi":"https://doi.org/10.14778/3685800.3685868","title":"An Interactive Multi-Modal Query Answering System with Retrieval-Augmented Large Language Models","display_name":"An Interactive Multi-Modal Query Answering System with Retrieval-Augmented Large Language Models","publication_year":2024,"publication_date":"2024-08-01","ids":{"openalex":"https://openalex.org/W4404181042","doi":"https://doi.org/10.14778/3685800.3685868"},"language":"en","primary_location":{"id":"doi:10.14778/3685800.3685868","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3685800.3685868","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","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/A5043365458","display_name":"Mengzhao Wang","orcid":"https://orcid.org/0000-0003-3806-1012"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengzhao Wang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100709658","display_name":"Haotian Wu","orcid":"https://orcid.org/0000-0001-5204-4388"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haotian Wu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071521429","display_name":"Xiangyu Ke","orcid":"https://orcid.org/0000-0001-8082-7398"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Ke","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006238145","display_name":"Yunjun Gao","orcid":"https://orcid.org/0000-0003-3816-8450"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunjun Gao","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112878526","display_name":"Xiaoliang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoliang Xu","raw_affiliation_strings":["Hangzhou Dianzi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100432093","display_name":"Lu Chen","orcid":"https://orcid.org/0000-0002-5685-7017"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Chen","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5311,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.84477005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"17","issue":"12","first_page":"4333","last_page":"4336"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9975000023841858,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9975000023841858,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9891999959945679,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9879000186920166,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.774757981300354},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7197315692901611},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6198819279670715},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.6158915758132935},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6158480048179626},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.615833580493927},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.532425582408905},{"id":"https://openalex.org/keywords/rdf-query-language","display_name":"RDF query language","score":0.5029112696647644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4417165219783783},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.33458542823791504},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.21113300323486328},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.21088609099388123},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.053889334201812744}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.774757981300354},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7197315692901611},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6198819279670715},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.6158915758132935},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6158480048179626},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.615833580493927},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.532425582408905},{"id":"https://openalex.org/C96956885","wikidata":"https://www.wikidata.org/wiki/Q6138701","display_name":"RDF query language","level":5,"score":0.5029112696647644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4417165219783783},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.33458542823791504},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.21113300323486328},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.21088609099388123},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.053889334201812744},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3685800.3685868","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3685800.3685868","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W3174809957","https://openalex.org/W4308450280","https://openalex.org/W4390647563","https://openalex.org/W4393065402","https://openalex.org/W4404534210"],"related_works":["https://openalex.org/W2572349046","https://openalex.org/W2096359267","https://openalex.org/W2392799717","https://openalex.org/W2169498276","https://openalex.org/W5304494","https://openalex.org/W2026738364","https://openalex.org/W2146885082","https://openalex.org/W2017989738","https://openalex.org/W1984397732","https://openalex.org/W3125756434"],"abstract_inverted_index":{"Retrieval-augmented":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"have":[5],"reshaped":[6],"traditional":[7],"query-answering":[8],"systems,":[9],"offering":[10],"unparalleled":[11],"user":[12],"experiences.":[13],"However,":[14],"existing":[15],"retrieval":[16,46,118],"techniques":[17],"often":[18],"struggle":[19],"to":[20,78,85,99],"handle":[21],"multi-modal":[22,45,161],"query":[23],"contexts.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28],"present":[29],"an":[30],"interactive":[31],"M":[32],"ulti-modal":[33],"Q":[34],"uery":[35],"A":[36,164],"nswering":[37],"(MQA)":[38],"system,":[39],"empowered":[40],"by":[41,74],"our":[42,120,133],"newly":[43],"developed":[44],"framework":[47],"and":[48,69,148],"navigation":[49,122],"graph":[50,123,146],"index,":[51,124],"integrated":[52],"with":[53],"cutting-edge":[54],"LLMs.":[55,149],"It":[56],"comprises":[57],"five":[58],"core":[59],"components:":[60],"Data":[61],"Preprocessing,":[62],"Vector":[63],"Representation,":[64],"Index":[65],"Construction,":[66],"Query":[67],"Execution,":[68],"Answer":[70],"Generation,":[71],"all":[72],"orchestrated":[73],"a":[75],"dedicated":[76],"coordinator":[77],"ensure":[79],"smooth":[80],"data":[81],"flow":[82],"from":[83,159],"input":[84],"answer":[86],"generation.":[87],"One":[88],"notable":[89],"aspect":[90],"of":[91,96,103,109,132,143,168],"MQA":[92,169],"is":[93,135,170],"its":[94,136],"utilization":[95],"contrastive":[97],"learning":[98],"assess":[100],"the":[101,114],"significance":[102],"different":[104],"modalities,":[105],"facilitating":[106],"precise":[107],"measurement":[108],"multimodal":[110],"information":[111],"similarity.":[112],"Furthermore,":[113],"system":[115,134],"achieves":[116],"efficient":[117],"through":[119],"advanced":[121],"refined":[125],"using":[126],"computational":[127],"pruning":[128],"techniques.":[129],"Another":[130],"highlight":[131],"pluggable":[137],"processing":[138],"framework,":[139],"allowing":[140],"seamless":[141],"integration":[142],"embedding":[144],"models,":[145],"indexes,":[147],"This":[150],"flexibility":[151],"provides":[152],"users":[153],"diverse":[154],"options":[155],"for":[156],"gaining":[157],"insights":[158],"their":[160],"knowledge":[162],"base.":[163],"preliminary":[165],"video":[166],"introduction":[167],"available":[171],"at":[172],"https://youtu.be/xvUuo2ZIqWk.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}