{"id":"https://openalex.org/W4412944243","doi":"https://doi.org/10.18653/v1/2025.magmar-1.5","title":"Multimodal Retrieval-Augmented Generation: Unified Information Processing Across Text, Image, Table, and Video Modalities","display_name":"Multimodal Retrieval-Augmented Generation: Unified Information Processing Across Text, Image, Table, and Video Modalities","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944243","doi":"https://doi.org/10.18653/v1/2025.magmar-1.5"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.magmar-1.5","doi":"https://doi.org/10.18653/v1/2025.magmar-1.5","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.magmar-1.5","pdf_url":"https://aclanthology.org/2025.magmar-1.5.pdf","source":{"id":"https://openalex.org/S7407121429","display_name":"Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR 2025)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2025.magmar-1.5.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014987268","display_name":"Nazarii Drushchak","orcid":"https://orcid.org/0000-0002-5056-3026","observed_orcids":["https://orcid.org/0000-0002-5056-3026"]},"institutions":[{"id":"https://openalex.org/I4210164689","display_name":"SoftServe (United States)","ror":"https://ror.org/05pqsb912","country_code":"US","type":"company","lineage":["https://openalex.org/I4210164689"]},{"id":"https://openalex.org/I4210165738","display_name":"Ukrainian Catholic University","ror":"https://ror.org/05tt5nr09","country_code":"UA","type":"education","lineage":["https://openalex.org/I4210165738"]}],"countries":["UA","US"],"is_corresponding":false,"raw_author_name":"Nazarii Drushchak","raw_affiliation_strings":["SoftServe Inc. ,","Ukrainian Catholic University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SoftServe Inc. ,","institution_ids":["https://openalex.org/I4210164689"]},{"raw_affiliation_string":"Ukrainian Catholic University ,","institution_ids":["https://openalex.org/I4210165738"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117156688","display_name":"Nataliya Polyakovska","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210164689","display_name":"SoftServe (United States)","ror":"https://ror.org/05pqsb912","country_code":"US","type":"company","lineage":["https://openalex.org/I4210164689"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nataliya Polyakovska","raw_affiliation_strings":["SoftServe Inc. ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SoftServe Inc. ,","institution_ids":["https://openalex.org/I4210164689"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117581821","display_name":"\u041c.\u0412. \u0411\u0430\u0443\u0442\u0456\u043d\u0430","orcid":"https://orcid.org/0009-0002-9617-9262","observed_orcids":["https://orcid.org/0009-0002-9617-9262"]},"institutions":[{"id":"https://openalex.org/I4210164689","display_name":"SoftServe (United States)","ror":"https://ror.org/05pqsb912","country_code":"US","type":"company","lineage":["https://openalex.org/I4210164689"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maryna Bautina","raw_affiliation_strings":["SoftServe Inc. ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SoftServe Inc. ,","institution_ids":["https://openalex.org/I4210164689"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119204163","display_name":"Taras Semenchenko","orcid":"https://orcid.org/0009-0007-3259-7007","observed_orcids":["https://orcid.org/0009-0007-3259-7007"]},"institutions":[{"id":"https://openalex.org/I189238007","display_name":"Taras Shevchenko National University of Kyiv","ror":"https://ror.org/02aaqv166","country_code":"UA","type":"education","lineage":["https://openalex.org/I189238007"]},{"id":"https://openalex.org/I4210164689","display_name":"SoftServe (United States)","ror":"https://ror.org/05pqsb912","country_code":"US","type":"company","lineage":["https://openalex.org/I4210164689"]}],"countries":["UA","US"],"is_corresponding":false,"raw_author_name":"Taras Semenchenko","raw_affiliation_strings":["SoftServe Inc. ,","Taras Shevchenko National University of Kyiv"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SoftServe Inc. ,","institution_ids":["https://openalex.org/I4210164689"]},{"raw_affiliation_string":"Taras Shevchenko National University of Kyiv","institution_ids":["https://openalex.org/I189238007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119204164","display_name":"Jakub Koscielecki","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210164689","display_name":"SoftServe (United States)","ror":"https://ror.org/05pqsb912","country_code":"US","type":"company","lineage":["https://openalex.org/I4210164689"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jakub Koscielecki","raw_affiliation_strings":["SoftServe Inc. ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SoftServe Inc. ,","institution_ids":["https://openalex.org/I4210164689"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119204165","display_name":"Wojciech Sykala","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210164689","display_name":"SoftServe (United States)","ror":"https://ror.org/05pqsb912","country_code":"US","type":"company","lineage":["https://openalex.org/I4210164689"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wojciech Sykala","raw_affiliation_strings":["SoftServe Inc. ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SoftServe Inc. ,","institution_ids":["https://openalex.org/I4210164689"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119204166","display_name":"Michal Wegrzynowski","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210164689","display_name":"SoftServe (United States)","ror":"https://ror.org/05pqsb912","country_code":"US","type":"company","lineage":["https://openalex.org/I4210164689"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michal Wegrzynowski","raw_affiliation_strings":["SoftServe Inc. ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SoftServe Inc. ,","institution_ids":["https://openalex.org/I4210164689"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.068,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8999235,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"59","last_page":"64"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9688000082969666,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9688000082969666,"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/T10028","display_name":"Topic Modeling","score":0.025100000202655792,"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":0.0035000001080334187,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9539999961853027},{"id":"https://openalex.org/keywords/multimodal-retrieval","display_name":"multimodal retrieval","score":0.8450000286102295},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6869999766349792},{"id":"https://openalex.org/keywords/document-indexing","display_name":"document indexing","score":0.5659999847412109},{"id":"https://openalex.org/keywords/structured-information-extraction","display_name":"structured data extraction","score":0.6050000190734863},{"id":"https://openalex.org/keywords/semantic-enrichment","display_name":"semantic enrichment","score":0.5540000200271606},{"id":"https://openalex.org/keywords/lookup-tables","display_name":"look-up table","score":0.5099999904632568},{"id":"https://openalex.org/keywords/image-based-questions","display_name":"image-based questions","score":0.7020000219345093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7894220352172852},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6245853900909424},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5400868058204651},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.517897367477417},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4058067500591278},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36940526962280273},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34614408016204834},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3250565528869629},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1339164674282074},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.magmar-1.5","doi":"https://doi.org/10.18653/v1/2025.magmar-1.5","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.magmar-1.5","pdf_url":"https://aclanthology.org/2025.magmar-1.5.pdf","source":{"id":"https://openalex.org/S7407121429","display_name":"Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR 2025)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.magmar-1.5","doi":"https://doi.org/10.18653/v1/2025.magmar-1.5","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.magmar-1.5","pdf_url":"https://aclanthology.org/2025.magmar-1.5.pdf","source":{"id":"https://openalex.org/S7407121429","display_name":"Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR 2025)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944243.pdf","grobid_xml":"https://content.openalex.org/works/W4412944243.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W4402466851","https://openalex.org/W4404330874","https://openalex.org/W4410089611","https://openalex.org/W4411119426"],"related_works":["https://openalex.org/W7206193260","https://openalex.org/W4389519872","https://openalex.org/W7166849397","https://openalex.org/W4415873442","https://openalex.org/W2181500363","https://openalex.org/W7166835336","https://openalex.org/W7196962421","https://openalex.org/W4412887933","https://openalex.org/W7134894356","https://openalex.org/W2171361956"],"abstract_inverted_index":{"Retrieval-augmented":[0,57],"generation":[1,58],"(RAG)":[2],"is":[3,132],"a":[4,54],"powerful":[5],"paradigm":[6],"for":[7,26,93,121,146],"leveraging":[8],"external":[9],"data":[10,40,74],"to":[11,62],"enhance":[12],"the":[13,110,134,141],"capabilities":[14],"of":[15,143],"large":[16],"language":[17],"models":[18],"(LLMs).However,":[19],"most":[20],"existing":[21],"RAG":[22],"solutions":[23],"are":[24],"tailored":[25],"single-modality":[27],"or":[28],"limited":[29],"multimodal":[30,87,135],"scenarios,":[31],"restricting":[32],"their":[33],"applicability":[34],"in":[35],"real-world":[36],"contexts":[37],"where":[38],"diverse":[39,147],"sources-including":[41],"text,":[42],"tables,":[43],"images,":[44],"and":[45,72,77,86,96,107,117,124,129],"videos-must":[46],"be":[47],"integrated":[48],"seamlessly.In":[49],"this":[50],"work,":[51],"we":[52],"propose":[53],"unified":[55,144],"Multimodal":[56],"(mRAG)":[59],"system":[60],"designed":[61],"unify":[63],"information":[64],"processing":[65],"across":[66],"all":[67],"four":[68],"modalities.Our":[69],"pipeline":[70],"ingests":[71],"indexes":[73],"from":[75],"PDFs":[76],"videos":[78],"using":[79],"tools":[80],"like":[81],"Amazon":[82],"Textract,":[83],"Transcribe,":[84],"Langfuse,":[85],"LLMs":[88],"(e.g.,":[89],"Claude":[90],"3.5":[91],"Sonnet)":[92],"structured":[94,122],"extraction":[95],"semantic":[97],"enrichment.The":[98],"dataset":[99],"includes":[100],"text":[101,123],"queries,":[102],"table":[103],"lookups,":[104],"image-based":[105],"questions,":[106],"videos.Evaluation":[108],"with":[109],"Deepeval":[111],"framework":[112,137],"shows":[113],"improved":[114],"retrieval":[115],"accuracy":[116],"response":[118],"quality,":[119],"especially":[120],"tables.While":[125],"performance":[126],"on":[127],"image":[128],"video":[130],"queries":[131],"lower,":[133],"integration":[136],"remains":[138],"robust,":[139],"underscoring":[140],"value":[142],"pipelines":[145],"data.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-10-10T00:00:00"}