{"id":"https://openalex.org/W7135211473","doi":"https://doi.org/10.48550/arxiv.2603.11223","title":"MDER-DR: Multi-Hop Question Answering with Entity-Centric Summaries","display_name":"MDER-DR: Multi-Hop Question Answering with Entity-Centric Summaries","publication_year":2026,"publication_date":"2026-03-11","ids":{"openalex":"https://openalex.org/W7135211473","doi":"https://doi.org/10.48550/arxiv.2603.11223"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.11223","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11223","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.11223","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120930678","display_name":"Riccardo Campi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Campi, Riccardo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039313308","display_name":"Nicol\u00f2 Oreste Pinciroli Vago","orcid":"https://orcid.org/0000-0001-7906-4987"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vago, Nicol\u00f2 Oreste Pinciroli","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003765523","display_name":"Mathyas Giudici","orcid":"https://orcid.org/0000-0002-4935-5131"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giudici, Mathyas","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129013829","display_name":"Marco Brambilla","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brambilla, Marco","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5087419988","display_name":"Piero Fraternali","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fraternali, Piero","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5120930678"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":0.5781999826431274,"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":0.5781999826431274,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.30979999899864197,"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":0.035100001841783524,"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/search-engine-indexing","display_name":"Search engine indexing","score":0.8694000244140625},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7049999833106995},{"id":"https://openalex.org/keywords/tree-traversal","display_name":"Tree traversal","score":0.5619000196456909},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5284000039100647},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4553000032901764},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.4262999892234802},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3847000002861023}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8694000244140625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7876999974250793},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7049999833106995},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6560999751091003},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.5619000196456909},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5284000039100647},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4553000032901764},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.4262999892234802},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C2778330532","wikidata":"https://www.wikidata.org/wiki/Q4826577","display_name":"Automatic indexing","level":3,"score":0.35409998893737793},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30720001459121704},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2858999967575073},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C96333769","wikidata":"https://www.wikidata.org/wiki/Q907955","display_name":"Graph traversal","level":3,"score":0.26570001244544983},{"id":"https://openalex.org/C176225458","wikidata":"https://www.wikidata.org/wiki/Q595971","display_name":"Graph database","level":3,"score":0.2606000006198883}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.11223","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11223","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.11223","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11223","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5131216049194336,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieval-Augmented":[0],"Generation":[1],"(RAG)":[2],"over":[3,154],"Knowledge":[4],"Graphs":[5],"(KGs)":[6],"suffers":[7],"from":[8,41],"the":[9,57,82,90,93,117],"fact":[10],"that":[11,54,106,131,143],"indexing":[12,58,64],"approaches":[13],"may":[14],"lose":[15],"important":[16],"contextual":[17],"nuance":[18],"when":[19],"text":[20],"is":[21,132,167],"reduced":[22],"to":[23,134,159],"triples,":[24],"thereby":[25],"degrading":[26],"performance":[27],"in":[28,89,116],"downstream":[29],"Question-Answering":[30],"(QA)":[31],"tasks,":[32],"particularly":[33],"for":[34,84],"multi-hop":[35],"QA,":[36],"which":[37],"requires":[38],"composing":[39],"answers":[40],"multiple":[42],"entities,":[43],"facts,":[44],"or":[45],"relations.":[46],"We":[47],"propose":[48],"a":[49,103],"domain-agnostic,":[50],"KG-based":[51],"QA":[52,94,129],"framework":[53],"covers":[55],"both":[56],"and":[59,73,113,124,137,146],"retrieval/inference":[60],"phases.":[61],"A":[62],"new":[63],"approach":[65],"called":[66],"Map-Disambiguate-Enrich-Reduce":[67],"(MDER)":[68],"generates":[69],"context-derived":[70],"triple":[71],"descriptions":[72],"subsequently":[74],"integrates":[75],"them":[76,115],"with":[77],"entity-level":[78],"summaries,":[79],"thus":[80],"avoiding":[81],"need":[83],"explicit":[85],"traversal":[86],"of":[87],"edges":[88],"graph":[91],"during":[92],"retrieval":[95,104],"phase.":[96],"Complementing":[97],"this,":[98],"we":[99],"introduce":[100],"Decompose-Resolve":[101],"(DR),":[102],"mechanism":[105],"decomposes":[107],"user":[108],"queries":[109],"into":[110],"resolvable":[111],"triples":[112],"grounds":[114],"KG":[118],"via":[119],"iterative":[120],"reasoning.":[121],"Together,":[122],"MDER":[123],"DR":[125],"form":[126],"an":[127],"LLM-driven":[128],"pipeline":[130],"robust":[133],"sparse,":[135],"incomplete,":[136],"complex":[138],"relational":[139],"data.":[140],"Experiments":[141],"show":[142],"on":[144],"standard":[145,155],"domain":[147],"specific":[148],"benchmarks,":[149],"MDER-DR":[150],"achieves":[151],"substantial":[152],"improvements":[153],"RAG":[156],"baselines":[157],"(up":[158],"66%),":[160],"while":[161],"maintaining":[162],"cross-lingual":[163],"robustness.":[164],"Our":[165],"code":[166],"available":[168],"at":[169],"https://github.com/DataSciencePolimi/MDER-DR_RAG.":[170]},"counts_by_year":[],"updated_date":"2026-03-14T06:46:50.379900","created_date":"2026-03-14T00:00:00"}