{"id":"https://openalex.org/W7155497163","doi":"https://doi.org/10.1109/icsc67292.2026.00010","title":"Automated Robust Dynamic Generation of KGQA Benchmark Datasets","display_name":"Automated Robust Dynamic Generation of KGQA Benchmark Datasets","publication_year":2026,"publication_date":"2026-02-02","ids":{"openalex":"https://openalex.org/W7155497163","doi":"https://doi.org/10.1109/icsc67292.2026.00010"},"language":null,"primary_location":{"id":"doi:10.1109/icsc67292.2026.00010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsc67292.2026.00010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Semantic Computing (ICSC)","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/A5134539716","display_name":"Aleksandr Gashkov","orcid":null},"institutions":[{"id":"https://openalex.org/I147765834","display_name":"Leipzig University of Applied Sciences","ror":"https://ror.org/03xgcq477","country_code":"DE","type":"education","lineage":["https://openalex.org/I147765834"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Aleksandr Gashkov","raw_affiliation_strings":["Leipzig University of Applied Sciences (HTWK Leipzig),Web & Software Engineering (WSE) Research Group,Leipzig,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leipzig University of Applied Sciences (HTWK Leipzig),Web & Software Engineering (WSE) Research Group,Leipzig,Germany","institution_ids":["https://openalex.org/I147765834"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047559751","display_name":"Aleksandr Perevalov","orcid":"https://orcid.org/0000-0002-6803-3357"},"institutions":[{"id":"https://openalex.org/I147765834","display_name":"Leipzig University of Applied Sciences","ror":"https://ror.org/03xgcq477","country_code":"DE","type":"education","lineage":["https://openalex.org/I147765834"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Aleksandr Perevalov","raw_affiliation_strings":["Leipzig University of Applied Sciences (HTWK Leipzig),Web & Software Engineering (WSE) Research Group,Leipzig,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leipzig University of Applied Sciences (HTWK Leipzig),Web & Software Engineering (WSE) Research Group,Leipzig,Germany","institution_ids":["https://openalex.org/I147765834"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075331649","display_name":"Maria Eltsova","orcid":"https://orcid.org/0000-0003-3792-8518"},"institutions":[{"id":"https://openalex.org/I41121874","display_name":"Heilbronn University","ror":"https://ror.org/04g5gcg95","country_code":"DE","type":"education","lineage":["https://openalex.org/I41121874"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maria Eltsova","raw_affiliation_strings":["CBZ München GmbH,CBZ Heilbronn,Heilbronn,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CBZ München GmbH,CBZ Heilbronn,Heilbronn,Germany","institution_ids":["https://openalex.org/I41121874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071736571","display_name":"Andreas Both","orcid":"https://orcid.org/0000-0002-9177-5463"},"institutions":[{"id":"https://openalex.org/I147765834","display_name":"Leipzig University of Applied Sciences","ror":"https://ror.org/03xgcq477","country_code":"DE","type":"education","lineage":["https://openalex.org/I147765834"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Both","raw_affiliation_strings":["Leipzig University of Applied Sciences (HTWK Leipzig),Web & Software Engineering (WSE) Research Group,Leipzig,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leipzig University of Applied Sciences (HTWK Leipzig),Web & Software Engineering (WSE) Research Group,Leipzig,Germany","institution_ids":["https://openalex.org/I147765834"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":19.9066,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.98938403,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"24","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.08550000190734863,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.08550000190734863,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10136","display_name":"Statistical Methods and Inference","score":0.05169999971985817,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.04230000078678131,"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/benchmark","display_name":"Benchmark (surveying)","score":0.4758000075817108},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3513999879360199},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.29179999232292175},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2833000123500824},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.26260000467300415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6136999726295471},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4758000075817108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4207000136375427},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40610000491142273},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3513999879360199},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29179999232292175},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2727999985218048},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26190000772476196},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25870001316070557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsc67292.2026.00010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsc67292.2026.00010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Semantic Computing (ICSC)","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":24,"referenced_works":["https://openalex.org/W150699991","https://openalex.org/W186369953","https://openalex.org/W2803728898","https://openalex.org/W2963900171","https://openalex.org/W2980401255","https://openalex.org/W3008811720","https://openalex.org/W3030844777","https://openalex.org/W3100058503","https://openalex.org/W3164228909","https://openalex.org/W3165041216","https://openalex.org/W3176757281","https://openalex.org/W4220844664","https://openalex.org/W4285192944","https://openalex.org/W4287027440","https://openalex.org/W4381329270","https://openalex.org/W4386834841","https://openalex.org/W4399699770","https://openalex.org/W4400529131","https://openalex.org/W4403615738","https://openalex.org/W4404724728","https://openalex.org/W4412377805","https://openalex.org/W4412844928","https://openalex.org/W4415080825","https://openalex.org/W7116799455"],"related_works":[],"abstract_inverted_index":{"Knowledge":[0,17],"Graph":[1],"Question":[2],"Answering":[3],"(KGQA)":[4],"systems":[5,37],"transform":[6],"natural-language":[7,97],"questions":[8],"into":[9],"structured":[10],"SPARQL":[11,106],"queries":[12,107],"to":[13,27,45,84,110,179,207],"retrieve":[14],"information":[15],"from":[16,56,160],"Graphs":[18],"(KGs).":[19],"However,":[20],"existing":[21,57],"KGQA":[22,75,114,235],"benchmarks":[23],"are":[24],"static,":[25],"prone":[26],"obsolescence":[28],"as":[29,165,167,195],"KGs":[30],"evolve,":[31],"and":[32,67,100,118,131,147,152,170,176,209,222,230],"increasingly":[33],"unreliable":[34],"for":[35,70,228],"evaluating":[36],"based":[38],"on":[39],"Large":[40],"Language":[41],"Models":[42],"(LLMs)":[43],"due":[44],"memorization":[46],"effects":[47],"(i.e.,":[48],"a":[49,64,203,211,226],"model":[50],"has":[51],"reproduced":[52],"the":[53,71,96,104,111,122,161,191,196],"correct":[54],"output":[55],"training":[58],"data).":[59],"This":[60],"paper":[61],"presents":[62],"DynBench,":[63],"fully":[65],"automated":[66,177],"robust":[68],"framework":[69],"dynamic":[72,156],"generation":[73],"of":[74,90,103,205,233],"benchmark":[76,92],"datasets.":[77],"Unlike":[78],"prior":[79],"approaches,":[80],"DynBench":[81,125,217],"is":[82],"enabled":[83],"automatically":[85,132],"generate":[86],"an":[87,140],"arbitrary":[88],"number":[89],"new":[91],"datasets":[93,163],"while":[94],"preserving":[95],"surface":[98],"forms":[99],"structural":[101],"complexity":[102],"original":[105,113],"in":[108],"comparison":[109],"given":[112],"dataset.":[115],"Using":[116],"entity":[117],"property":[119],"substitutions":[120],"within":[121],"same":[123],"KG,":[124],"produces":[126],"semantically":[127],"consistent":[128],"question-query":[129],"pairs":[130],"validates":[133],"them":[134],"without":[135],"human":[136,174,215],"intervention.":[137],"We":[138],"introduce":[139],"automatic":[141,199],"validation":[142,200],"mechanism":[143],"that":[144,190],"ensures":[145],"semantic":[146],"syntactic":[148],"integrity":[149],"through":[150],"back-transformation":[151],"metric-based":[153],"validation.":[154],"Two":[155],"bench-marks":[157],"were":[158],"generated":[159],"well-known":[162],"QALD-9-plus":[164],"well":[166],"LC-QuAD":[168],"2.0":[169],"evaluated":[171],"using":[172],"both":[173],"experts":[175],"metrics":[178],"show":[180],"DynBench\u2019s":[181],"dataset-agnostic":[182],"capabilities.":[183],"Given":[184],"our":[185],"results,":[186],"we":[187],"can":[188],"infer":[189],"Levenshtein":[192],"distance":[193],"serves":[194],"most":[197],"reliable":[198],"measure,":[201],"achieving":[202],"precision":[204],"up":[206],"0.96":[208],"demonstrating":[210],"strong":[212],"correlation":[213],"with":[214],"assessments.":[216],"thus":[218],"enables":[219],"scalable,":[220],"repeatable,":[221],"memorization-resistant":[223],"dataset":[224],"generation\u2014providing":[225],"foundation":[227],"sustainable":[229],"fair":[231],"evaluation":[232],"LLM-based":[234],"systems.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2026-04-25T00:00:00"}