{"id":"https://openalex.org/W4416249945","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228599","title":"Benchmarking Retrieval-Augmented Generation: Challenging Domain-specific Datasets Generation Method","display_name":"Benchmarking Retrieval-Augmented Generation: Challenging Domain-specific Datasets Generation Method","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416249945","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228599"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100360935","display_name":"Yanqing Liu","orcid":"https://orcid.org/0000-0003-0412-8805"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanqing Liu","raw_affiliation_strings":["Xi’an Jiaotong University,School of Software Engineering,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Software Engineering,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091321590","display_name":"Lei Hu","orcid":"https://orcid.org/0000-0003-3562-9178"},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]},{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Hu","raw_affiliation_strings":["University of California,Computer Science Department,San Diego,California,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Computer Science Department,San Diego,California,United States","institution_ids":["https://openalex.org/I36258959","https://openalex.org/I2803209242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052586934","display_name":"Xiaolong Dong","orcid":"https://orcid.org/0000-0001-9515-9281"},"institutions":[{"id":"https://openalex.org/I4210099297","display_name":"Jilian Technology Group (China)","ror":"https://ror.org/016q5ce10","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210099297"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolong Dong","raw_affiliation_strings":["Hangzhou Yanqu Information Technology Co., Ltd,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Yanqu Information Technology Co., Ltd,Hangzhou,China","institution_ids":["https://openalex.org/I4210099297"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100376381","display_name":"Zhi Wang","orcid":"https://orcid.org/0000-0002-0490-2031"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Wang","raw_affiliation_strings":["Xi’an Jiaotong University,School of Software Engineering,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Software Engineering,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16504806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.39489999413490295,"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":0.39489999413490295,"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":0.1678999960422516,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.12470000237226486,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8978999853134155},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8048999905586243},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.6779000163078308},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5702999830245972},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.35019999742507935}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8978999853134155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8072999715805054},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8048999905586243},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.6779000163078308},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5702999830245972},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4487000107765198},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3896999955177307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3896999955177307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3736000061035156},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.31709998846054077},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.2556000053882599}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2889787757","https://openalex.org/W2912924812","https://openalex.org/W2963339397","https://openalex.org/W4309674289","https://openalex.org/W4385565351","https://openalex.org/W4386576685","https://openalex.org/W4389518998","https://openalex.org/W4400531953","https://openalex.org/W4401042808","https://openalex.org/W4402670290","https://openalex.org/W4403560390","https://openalex.org/W4404781771","https://openalex.org/W4404783220","https://openalex.org/W4404783567","https://openalex.org/W4406771321","https://openalex.org/W4411119426","https://openalex.org/W4411630045","https://openalex.org/W4416037024"],"related_works":[],"abstract_inverted_index":{"Retrieval-Augmented":[0],"Generation":[1],"(RAG)":[2],"enhances":[3],"the":[4,118,128,154,161,170,180,195,211,223],"answering":[5,104,192],"capabilities":[6],"of":[7,117,120,130,163,178,187,205,213,227],"large":[8],"language":[9],"models":[10],"(LLMs)":[11],"by":[12],"leveraging":[13],"knowledge":[14],"retrieved":[15],"from":[16,140],"external":[17],"corpora,":[18],"significantly":[19],"mitigating":[20],"hallucination":[21],"issues":[22],"in":[23,68,73,123,210],"LLMs.":[24],"RAG":[25,36,58,70,89,97,121,228],"systems":[26,37,122,229],"have":[27],"been":[28],"widely":[29],"applied":[30],"across":[31],"various":[32],"domains.":[33,75,125,233],"However,":[34],"existing":[35],"often":[38],"rely":[39],"on":[40,45,107],"LLMs":[41,198],"and":[42,103,137,148,156,208,225,235],"retrievers":[43],"trained":[44],"general-purpose":[46],"datasets,":[47],"which":[48],"perform":[49],"poorly":[50],"when":[51],"dealing":[52],"with":[53,100],"domain-specific":[54,84,96,132],"tasks.":[55],"Furthermore,":[56],"current":[57],"bench-mark":[59],"datasets":[60,85,99,113,134,172,181],"fail":[61],"to":[62,152,185],"cover":[63],"all":[64],"domains,":[65],"posing":[66],"challenges":[67,102,183],"evaluating":[69],"systems\u2019":[71],"performance":[72,119],"specific":[74,124,232],"To":[76],"address":[77],"these":[78],"limitations,":[79],"we":[80],"propose":[81],"a":[82,202],"challenging":[83],"generation":[86],"method":[87,93],"for":[88,231],"benchmarking":[90],"(RAGCDs).":[91],"This":[92,159],"automatically":[94],"generates":[95],"benchmark":[98,133],"retrieval":[101,189,214],"difficulties":[105],"based":[106],"any":[108],"given":[109],"corpus.":[110],"The":[111],"generated":[112],"enable":[114],"rigorous":[115],"evaluation":[116],"We":[126,216],"detail":[127],"process":[129],"constructing":[131],"using":[135],"RAGCDs":[136,219],"select":[138],"corpora":[139],"two":[141],"distinct":[142],"fields,":[143],"X-ray":[144],"Photoelectron":[145],"Spectroscopy":[146],"(XPS)":[147],"medical":[149],"research":[150],"papers,":[151],"create":[153],"CDs-xps":[155],"CDs-medical":[157],"datasets.":[158],"demonstrates":[160],"generality":[162],"our":[164],"method.":[165],"Our":[166],"experiments":[167],"validate":[168],"that":[169,218],"RAGCDs-generated":[171],"exhibit":[173],"exceptional":[174],"quality.":[175],"In":[176],"terms":[177],"retrieval,":[179],"pose":[182],"comparable":[184],"those":[186],"specialized":[188],"benchmarks.":[190],"Regarding":[191],"difficulty,":[193],"even":[194],"most":[196],"advanced":[197],"struggle":[199],"significantly,":[200],"achieving":[201],"score":[203],"ratio":[204],"only":[206],"0.391":[207],"0.471":[209],"absence":[212],"support.":[215],"hope":[217],"will":[220],"effectively":[221],"promote":[222],"development":[224],"optimization":[226],"tailored":[230],"Implementation":[234],"data":[236],"are":[237],"available":[238],"at":[239],"https://github.com/xiaowuxiaowu1/RAGCDs.":[240]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-14T00:00:00"}