{"id":"https://openalex.org/W7167916203","doi":"https://doi.org/10.1145/3805712.3809693","title":"Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation","display_name":"Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167916203","doi":"https://doi.org/10.1145/3805712.3809693"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809693","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809693","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809693","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061263278","display_name":"Yuchen Yan","orcid":"https://orcid.org/0009-0005-8672-4468"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuchen Yan","raw_affiliation_strings":["Department of Computer Science, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0005-8672-4468","affiliations":[{"raw_affiliation_string":"Department of Computer Science, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073382156","display_name":"Peiyan Zhang","orcid":"https://orcid.org/0000-0002-8691-1846"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Peiyan Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-8691-1846","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140383797","display_name":"Zhihua Liu","orcid":"https://orcid.org/0009-0001-7330-5601"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Zhihua Liu","raw_affiliation_strings":["Samsung R&D institute China-Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-7330-5601","affiliations":[{"raw_affiliation_string":"Samsung R&D institute China-Beijing, Beijing, China","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140445897","display_name":"Hao Wang","orcid":"https://orcid.org/0009-0002-5150-5204"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Samsung R&D institute China-Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-5150-5204","affiliations":[{"raw_affiliation_string":"Samsung R&D institute China-Beijing, Beijing, China","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045777220","display_name":"Yatao Bian","orcid":"https://orcid.org/0000-0002-2368-4084"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yatao Bian","raw_affiliation_strings":["Department of Computer Science, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-2368-4084","affiliations":[{"raw_affiliation_string":"Department of Computer Science, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100695258","display_name":"Weiming Li","orcid":"https://orcid.org/0000-0003-4054-5956"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Weiming Li","raw_affiliation_strings":["Samsung R&D institute China-Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4054-5956","affiliations":[{"raw_affiliation_string":"Samsung R&D institute China-Beijing, Beijing, China","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016760086","display_name":"Xiaoshuai Hao","orcid":"https://orcid.org/0009-0007-4209-6695"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshuai Hao","raw_affiliation_strings":["Xiaomi EV, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-4209-6695","affiliations":[{"raw_affiliation_string":"Xiaomi EV, Beijing, China","institution_ids":["https://openalex.org/I862669128"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"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":"2150","last_page":"2161"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6421999931335449,"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":0.6421999931335449,"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":0.1062999963760376,"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":0.07180000096559525,"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/feature-learning","display_name":"Feature learning","score":0.5701000094413757},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5437999963760376},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4584999978542328},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.4050000011920929},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.3871000111103058},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.3684999942779541},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.34599998593330383},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3400000035762787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8188999891281128},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5701000094413757},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5437999963760376},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4584999978542328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4575999975204468},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39660000801086426},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36719998717308044},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3066999912261963},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809693","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809693","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809693","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809693","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7347742915153503}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2096733369","https://openalex.org/W2127978399","https://openalex.org/W2251913848","https://openalex.org/W2979826702","https://openalex.org/W2998496395","https://openalex.org/W3190126809","https://openalex.org/W4251326898","https://openalex.org/W4378506766","https://openalex.org/W4386076359","https://openalex.org/W4387848931","https://openalex.org/W4389519118","https://openalex.org/W4391451952","https://openalex.org/W4392089494","https://openalex.org/W4399657602","https://openalex.org/W4400525788","https://openalex.org/W4401857375","https://openalex.org/W4404835216","https://openalex.org/W4404954244","https://openalex.org/W4411119286","https://openalex.org/W4411120544","https://openalex.org/W4412376976","https://openalex.org/W4415797504","https://openalex.org/W4415800738","https://openalex.org/W7133217724"],"related_works":[],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1,175],"(RAG)":[2],"has":[3],"demonstrated":[4],"its":[5,163],"ability":[6,164],"to":[7,29,48,60,96,165],"enhance":[8,162],"Large":[9],"Language":[10],"Models":[11],"(LLMs)":[12],"by":[13,143],"integrating":[14],"external":[15],"knowledge":[16,27],"sources.":[17],"However,":[18],"multi-hop":[19,42,83,107,191],"questions,":[20],"which":[21,146],"require":[22],"the":[23,41,51,64,124,138,144,157,179,185,197],"identification":[24],"of":[25,66,106,159,187],"multiple":[26,67],"targets":[28],"form":[30],"a":[31,76,89,102,114],"synthesized":[32,173],"answer,":[33],"raise":[34],"new":[35],"challenges":[36],"for":[37,82,101,120,177],"RAG":[38],"systems.":[39],"Under":[40],"settings,":[43],"existing":[44],"methods":[45],"often":[46],"struggle":[47],"fully":[49],"understand":[50],"questions":[52,196],"with":[53],"complex":[54],"semantic":[55],"structures":[56],"and":[57,133],"are":[58],"susceptible":[59],"irrelevant":[61],"noise":[62],"during":[63],"retrieval":[65],"information":[68,99,139,151],"targets.":[69],"To":[70,161],"address":[71],"these":[72],"limitations,":[73],"we":[74,112,169],"propose":[75,171],"novel":[77],"graph":[78],"representation":[79,121],"learning":[80,122],"framework":[81,189],"question":[84],"retrieval.":[85],"We":[86],"first":[87],"introduce":[88],"Multi-information":[90],"Level":[91],"Knowledge":[92],"Graph":[93,116],"(Multi-L":[94],"KG)":[95],"model":[97],"various":[98],"levels":[100],"more":[103],"comprehensive":[104],"understanding":[105],"questions.":[108],"Based":[109],"on":[110,123],"this,":[111],"design":[113],"Question-Adaptive":[115],"Neural":[117],"Network":[118],"(Quest-GNN)":[119],"Multi-L":[125],"KG.":[126],"Quest-GNN":[127],"employs":[128],"intra/inter-level":[129],"message":[130,136],"passing":[131,137],"mechanisms,":[132],"in":[134,190,194],"each":[135],"aggregation":[140,152],"is":[141,204],"guided":[142],"question,":[145],"not":[147],"only":[148],"facilitates":[149],"multi-granular":[150],"but":[153],"also":[154],"significantly":[155],"reduces":[156],"impact":[158],"noise.":[160],"learn":[166],"robust":[167],"representations,":[168],"further":[170],"two":[172],"data":[174],"strategies":[176],"pre-training":[178],"Quest-GNN.":[180],"Extensive":[181],"experimental":[182],"results":[183],"demonstrate":[184],"effectiveness":[186],"our":[188],"scenarios,":[192],"especially":[193],"high-hop":[195],"improvement":[198],"can":[199],"reach":[200],"33.8%.":[201],"The":[202],"code":[203],"available":[205],"at:":[206],"https://github.com/Jerry2398/QSGNN.":[207]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-11T00:00:00"}