{"id":"https://openalex.org/W7164653609","doi":"https://doi.org/10.1145/3805712.3809925","title":"How Fine-Grained Should a RAG Benchmark Be? A Hierarchical Framework for Synthetic Question Generation","display_name":"How Fine-Grained Should a RAG Benchmark Be? A Hierarchical Framework for Synthetic Question Generation","publication_year":2026,"publication_date":"2026-07-15","ids":{"openalex":"https://openalex.org/W7164653609","doi":"https://doi.org/10.1145/3805712.3809925"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809925","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809925","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809925","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5095091852","display_name":"Chase Fensore","orcid":null},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chase M. Fensore","raw_affiliation_strings":["Department of Computer Science, Emory University, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0009-0007-6761-1809","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138563575","display_name":"Kaustubh Dhole","orcid":null},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaustubh Dhole","raw_affiliation_strings":["Department of Computer Science, Emory University, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8875-176X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105586716","display_name":"Jason Fan","orcid":"https://orcid.org/0009-0003-3728-9960"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Fan","raw_affiliation_strings":["Department of Computer Science, Emory University, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0009-0004-6648-4164","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028578280","display_name":"Eugene Agichtein","orcid":"https://orcid.org/0000-0002-3148-5448"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Agichtein","raw_affiliation_strings":["Department of Computer Science, Emory University, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3148-5448","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135786089","display_name":"Joyce C. Ho","orcid":null},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joyce C. Ho","raw_affiliation_strings":["Department of Computer Science, Emory University, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9168-3916","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150468666"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3715","last_page":"3720"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8147000074386597,"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":0.8147000074386597,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.120899997651577,"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"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.008799999952316284,"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/granularity","display_name":"Granularity","score":0.9483000040054321},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7627000212669373},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7602999806404114},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7444999814033508},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5023000240325928},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.49720001220703125},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4092000126838684}],"concepts":[{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.9483000040054321},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7627000212669373},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7602999806404114},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7444999814033508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5898000001907349},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5023000240325928},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.49720001220703125},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4832000136375427},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40639999508857727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3758000135421753},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3411000072956085},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2800999879837036},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26109999418258667},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3805712.3809925","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809925","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"},{"id":"pmh:oai:arXiv.org:2606.12789","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.12789","pdf_url":"https://arxiv.org/pdf/2606.12789","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809925","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809925","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":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7445106506347656}],"awards":[{"id":"https://openalex.org/G2477648378","display_name":null,"funder_award_id":"IIS-2145411","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3494058236","display_name":"CAREER: Aequitas: A comprehensive machine learning framework to decode health disparities","funder_award_id":"2145411","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5770373782","display_name":"The CSGrad4US Fellowship Program","funder_award_id":"2313998","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332169","display_name":"Directorate for Computer and Information Science and Engineering","ror":"https://ror.org/025kzpk63"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Evaluating":[0],"retrieval-augmented":[1],"generation":[2,53],"(RAG)":[3],"systems":[4],"requires":[5],"benchmarks":[6],"that":[7,45],"capture":[8],"diverse":[9],"question":[10],"characteristics,":[11],"yet":[12],"practitioners":[13,174],"lack":[14],"empirical":[15],"guidance":[16],"on":[17],"which":[18],"dimensions":[19,77,139],"to":[20,126,175],"vary":[21],"and":[22,90,113,170],"at":[23,84,117],"what":[24],"granularity.":[25,119],"We":[26,120],"present":[27],"HieraRAG,":[28],"a":[29,58,63,94,122,162,167],"hierarchical":[30],"framework":[31],"for":[32,173],"studying":[33],"granularity":[34,41,86,98,178],"in":[35],"RAG":[36,60,182],"benchmark":[37],"construction,":[38],"defining":[39],"optimal":[40,97],"as":[42],"the":[43],"level":[44],"maximizes":[46],"discriminative":[47],"power":[48],"(the":[49],"standard":[50],"deviation":[51],"of":[52,149],"quality":[54],"across":[55,75,138],"categories)":[56],"within":[57,179],"given":[59],"configuration.":[61],"As":[62],"case":[64],"study,":[65],"we":[66],"generate":[67],"5,872":[68],"synthetic":[69,155],"question-answer":[70],"(QA)":[71],"pairs":[72,153],"from":[73,104],"FineWeb-10BT":[74],"3":[76,85],"(Question":[78,140],"Complexity,":[79],"Answer":[80,144],"Type,":[81],"Linguistic":[82],"Variation)":[83],"levels":[87],"(2,":[88],"4,":[89],"8":[91],"categories).":[92],"With":[93],"BM25+Falcon-3-10B":[95],"pipeline,":[96],"varies":[99],"by":[100],"dimension:":[101],"complexity":[102],"benefits":[103],"fine-grained":[105,129],"distinctions":[106],"(discriminative":[107],"power:":[108],"0.053)":[109],"while":[110],"answer":[111],"type":[112],"linguistic":[114],"variation":[115],"peak":[116],"medium":[118],"introduce":[121],"Coherence":[123],"Ratio":[124],"metric":[125,172],"quantify":[127],"whether":[128],"splits":[130],"cleanly":[131],"subdivide":[132],"parent":[133],"categories,":[134],"revealing":[135],"structural":[136],"differences":[137],"Complexity:":[141],"0.40":[142],"vs.":[143],"Type:":[145],"1.44).":[146],"Human":[147],"evaluation":[148,177],"110":[150],"stratified":[151],"QA":[152],"confirms":[154],"quality.":[156],"While":[157],"these":[158],"specific":[159],"findings":[160],"reflect":[161],"single":[163],"configuration,":[164],"HieraRAG":[165],"provides":[166],"portable":[168],"procedure":[169],"validation":[171],"determine":[176],"their":[180],"own":[181],"settings.":[183]},"counts_by_year":[],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2026-06-14T00:00:00"}