{"id":"https://openalex.org/W4416852254","doi":"https://doi.org/10.1145/3770854.3780171","title":"Mixture-of-RAG: Integrating Text and Tables with Large Language Models","display_name":"Mixture-of-RAG: Integrating Text and Tables with Large Language Models","publication_year":2025,"publication_date":"2025-04-13","ids":{"openalex":"https://openalex.org/W4416852254","doi":"https://doi.org/10.1145/3770854.3780171"},"language":"en","primary_location":{"id":"doi:10.1145/3770854.3780171","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3780171","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3770854.3780171","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100458169","display_name":"Chi Zhang","orcid":"https://orcid.org/0000-0002-2995-7469"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi Zhang","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-0323-0715","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042326787","display_name":"Qiyang Chen","orcid":"https://orcid.org/0000-0002-7804-8835"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiyang Chen","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-0913-1970","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100751725","display_name":"Mengqi Zhang","orcid":"https://orcid.org/0000-0002-8354-7129"},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengqi Zhang","raw_affiliation_strings":["Zhejiang Gongshang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0009-4349-6177","affiliations":[{"raw_affiliation_string":"Zhejiang Gongshang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I75059550"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.34776311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1880","last_page":"1891"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5651999711990356,"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":0.5651999711990356,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.09939999878406525,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.07590000331401825,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.6233999729156494},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.592199981212616},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.5695000290870667},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.531000018119812},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49309998750686646},{"id":"https://openalex.org/keywords/hierarchical-database-model","display_name":"Hierarchical database model","score":0.4643000066280365},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4163999855518341},{"id":"https://openalex.org/keywords/grammaticality","display_name":"Grammaticality","score":0.39469999074935913},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3862000107765198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8296999931335449},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.6233999729156494},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5963000059127808},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.592199981212616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5835999846458435},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5695000290870667},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.531000018119812},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49309998750686646},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.4643000066280365},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C2779525943","wikidata":"https://www.wikidata.org/wiki/Q1187300","display_name":"Grammaticality","level":3,"score":0.39469999074935913},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3862000107765198},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3846000134944916},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29089999198913574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28209999203681946},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3770854.3780171","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3780171","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.09554","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.09554","pdf_url":"https://arxiv.org/pdf/2504.09554","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.09554","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.09554","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,"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3770854.3780171","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3780171","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"achieve":[4],"optimal":[5],"utility":[6],"when":[7],"their":[8,53],"responses":[9],"are":[10],"grounded":[11],"in":[12,130],"external":[13,50],"knowledge":[14],"sources.":[15],"However,":[16],"real-world":[17],"documents,":[18],"such":[19,59],"as":[20],"annual":[21],"reports,":[22],"scientific":[23],"papers,":[24],"and":[25,79,83,103,116,150,170],"clinical":[26],"guidelines,":[27],"frequently":[28],"combine":[29],"extensive":[30],"narrative":[31],"content":[32],"with":[33,49,110,145],"complex,":[34],"hierarchically":[35],"structured":[36],"tables.":[37],"While":[38],"existing":[39],"retrieval-augmented":[40],"generation":[41],"(RAG)":[42],"systems":[43],"effectively":[44],"integrate":[45],"LLMs'":[46],"generative":[47],"capabilities":[48],"retrieval-based":[51],"information,":[52],"performance":[54,176],"significantly":[55],"deteriorates":[56],"especially":[57],"processing":[58],"heterogeneous":[60,104],"text-table":[61,148],"hierarchies.":[62],"To":[63,126],"address":[64],"this":[65,134],"limitation,":[66],"we":[67,136],"formalize":[68],"the":[69,128,138],"task":[70],"of":[71],"Heterogeneous":[72],"Document":[73],"RAG,":[74],"which":[75],"requires":[76],"joint":[77],"retrieval":[78,163],"reasoning":[80,119],"across":[81],"textual":[82],"hierarchical":[84,101],"tabular":[85],"data.":[86],"We":[87],"propose":[88],"MixRAG,":[89],"a":[90,122,141],"novel":[91],"three-stage":[92],"framework:":[93],"(i)":[94],"hierarchy":[95],"row-and-column-level":[96],"(H-RCL)":[97],"representation":[98],"that":[99,159],"preserves":[100],"structure":[102],"relationship,":[105],"(ii)":[106],"an":[107],"ensemble":[108],"retriever":[109],"LLM-based":[111],"reranking":[112],"for":[113,133,177],"evidence":[114],"alignment,":[115],"(iii)":[117],"multi-step":[118],"decomposition":[120],"via":[121],"RECAP":[123],"prompt":[124],"strategy.":[125],"bridge":[127],"gap":[129],"available":[131],"data":[132],"domain,":[135],"release":[137],"dataset":[139],"DocRAGLib,":[140],"2k-document":[142],"corpus":[143],"paired":[144],"automatically":[146],"aligned":[147],"summaries":[149],"gold":[151],"document":[152,179],"annotations.":[153],"The":[154],"comprehensive":[155],"experiment":[156],"results":[157],"demonstrate":[158],"MixRAG":[160],"boosts":[161],"top-1":[162],"by":[164],"46%":[165],"over":[166],"strong":[167],"text-only,":[168],"table-only,":[169],"naive-mixture":[171],"baselines,":[172],"establishing":[173],"new":[174],"state-of-the-art":[175],"mixed-modality":[178],"grounding.":[180]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}