{"id":"https://openalex.org/W7156812889","doi":"https://doi.org/10.48550/arxiv.2604.23783","title":"S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA","display_name":"S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA","publication_year":2026,"publication_date":"2026-04-26","ids":{"openalex":"https://openalex.org/W7156812889","doi":"https://doi.org/10.48550/arxiv.2604.23783"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.23783","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23783","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.2604.23783","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134819451","display_name":"Minghan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Minghan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052070029","display_name":"Junjie Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, Junjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123348231","display_name":"Xinxuan Lv","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lv, Xinxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134797442","display_name":"Chao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134777758","display_name":"Guodong Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Guodong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5134819451"],"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":0.9302999973297119,"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":0.9302999973297119,"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":0.018799999728798866,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.009200000204145908,"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/question-answering","display_name":"Question answering","score":0.6491000056266785},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6341000199317932},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5026999711990356},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4357999861240387},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42419999837875366},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41999998688697815},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.4101000130176544},{"id":"https://openalex.org/keywords/iterative-refinement","display_name":"Iterative refinement","score":0.388700008392334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.720300018787384},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6491000056266785},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6341000199317932},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5026999711990356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44769999384880066},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4357999861240387},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41999998688697815},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41929998993873596},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41929998993873596},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.4101000130176544},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.388700008392334},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35580000281333923},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31130000948905945},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.23783","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23783","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.2604.23783","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23783","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":[],"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],"grounds":[3],"language":[4],"models":[5],"in":[6],"external":[7],"evidence,":[8],"but":[9],"multi-hop":[10,142],"question":[11],"answering":[12,82],"remains":[13],"difficult":[14],"because":[15],"iterative":[16,64],"pipelines":[17,158],"must":[18],"control":[19],"what":[20],"to":[21],"retrieve":[22],"next":[23,103],"and":[24,53,60,136,145],"when":[25],"the":[26,77,92,102,165,170],"available":[27],"evidence":[28,38,79],"is":[29],"adequate.":[30],"In":[31],"practice,":[32],"systems":[33],"may":[34,42],"answer":[35],"from":[36,129],"incomplete":[37],"chains,":[39],"or":[40,45,168],"they":[41],"accumulate":[43],"redundant":[44],"distractor-heavy":[46],"text":[47],"that":[48,90,139],"interferes":[49],"with":[50,66],"later":[51],"retrieval":[52,104,109],"reasoning.":[54],"We":[55],"propose":[56],"S2G-RAG":[57,115,140,151],"(Structured":[58],"Sufficiency":[59],"Gap-judging":[61],"RAG),":[62],"an":[63,67],"framework":[65],"explicit":[68],"controller,":[69],"S2G-Judge.":[70],"At":[71],"each":[72],"turn,":[73],"S2G-Judge":[74],"predicts":[75],"whether":[76],"current":[78],"memory":[80],"supports":[81],"and,":[83],"if":[84],"not,":[85],"outputs":[86],"structured":[87],"gap":[88,96],"items":[89,97],"describe":[91],"missing":[93],"information.":[94],"These":[95],"are":[98],"then":[99],"mapped":[100],"into":[101,155],"query,":[105],"producing":[106],"stable":[107],"multi-turn":[108,148],"trajectories.":[110],"To":[111],"reduce":[112],"noise":[113],"accumulation,":[114],"maintains":[116],"a":[117,123,160],"sentence-level":[118],"Evidence":[119],"Context":[120],"by":[121],"extracting":[122],"compact":[124],"set":[125],"of":[126],"relevant":[127],"sentences":[128],"retrieved":[130],"documents.":[131],"Experiments":[132],"on":[133],"TriviaQA,":[134],"HotpotQA,":[135],"2WikiMultiHopQA":[137],"show":[138],"improves":[141],"QA":[143],"performance":[144],"robustness":[146],"under":[147],"retrieval.":[149],"Furthermore,":[150],"can":[152],"be":[153],"integrated":[154],"existing":[156],"RAG":[157],"as":[159],"lightweight":[161],"component,":[162],"without":[163],"modifying":[164],"search":[166],"engine":[167],"retraining":[169],"generator.":[171]},"counts_by_year":[],"updated_date":"2026-04-29T06:16:36.941037","created_date":"2026-04-29T00:00:00"}