{"id":"https://openalex.org/W4415152165","doi":"https://doi.org/10.63317/5mcjipa88zjm","title":"MHTS: Multi-Hop Tree Structure Framework for Generating Difficulty-Controllable QA Datasets for RAG Evaluation","display_name":"MHTS: Multi-Hop Tree Structure Framework for Generating Difficulty-Controllable QA Datasets for RAG Evaluation","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W4415152165","doi":"https://doi.org/10.63317/5mcjipa88zjm"},"language":"en","primary_location":{"id":"doi:10.63317/5mcjipa88zjm","is_oa":false,"landing_page_url":"https://doi.org/10.63317/5mcjipa88zjm","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.08756","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100627578","display_name":"Jeong-Soo Lee","orcid":"https://orcid.org/0000-0002-8491-4429"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeongsoo Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021221217","display_name":"Daeyong Kwon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daeyong Kwon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028883212","display_name":"Kyohoon Jin","orcid":"https://orcid.org/0000-0002-7824-3577"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyohoon Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108665442","display_name":"J.-H. Jeong","orcid":"https://orcid.org/0009-0006-3310-5265"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"JunNyeong Jeong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119987433","display_name":"Minwoo Sim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minwoo Sim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5054579775","display_name":"Minwoo Kim","orcid":"https://orcid.org/0000-0001-5640-4029"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minwoo Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.00520648,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5158","last_page":"5168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.8127999901771545,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.8127999901771545,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7799000144004822},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7121999859809875},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6187999844551086},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5820000171661377},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.4383000135421753},{"id":"https://openalex.org/keywords/decision-tree-model","display_name":"Decision tree model","score":0.3504999876022339}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7799000144004822},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7394000291824341},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7121999859809875},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6187999844551086},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5927000045776367},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5820000171661377},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5145000219345093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4578999876976013},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.4383000135421753},{"id":"https://openalex.org/C56289965","wikidata":"https://www.wikidata.org/wiki/Q5249246","display_name":"Decision tree model","level":3,"score":0.3504999876022339},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2615000009536743}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.63317/5mcjipa88zjm","is_oa":false,"landing_page_url":"https://doi.org/10.63317/5mcjipa88zjm","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.08756","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.08756","pdf_url":"https://arxiv.org/pdf/2504.08756","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.08756","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.08756","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.08756","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.08756","pdf_url":"https://arxiv.org/pdf/2504.08756","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"RAG":[1,93,116],"benchmarks":[2],"often":[3],"overlook":[4],"query":[5],"difficulty,":[6,29],"leading":[7],"to":[8,71],"inflated":[9],"performance":[10,89],"on":[11,37],"simpler":[12],"questions":[13],"and":[14,28,39,102,110,118],"unreliable":[15],"evaluations.":[16],"A":[17],"robust":[18],"benchmark":[19],"dataset":[20,56],"must":[21],"satisfy":[22],"three":[23],"key":[24],"criteria:":[25],"quality,":[26],"diversity,":[27],"which":[30],"capturing":[31],"the":[32,40,87],"complexity":[33,64],"of":[34,42,91],"reasoning":[35,63],"based":[36],"hops":[38],"distribution":[41],"supporting":[43],"evidence.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"propose":[49],"MHTS":[50],"(Multi-Hop":[51],"Tree":[52],"Structure),":[53],"a":[54,67,83,92],"novel":[55],"synthesis":[57],"framework":[58],"that":[59],"systematically":[60],"controls":[61],"multi-hop":[62,68],"by":[65],"leveraging":[66],"tree":[69],"structure":[70],"generate":[72],"logically":[73],"connected,":[74],"multi-chunk":[75],"queries.":[76],"Our":[77],"fine-grained":[78],"difficulty":[79],"estimation":[80],"formula":[81],"exhibits":[82],"strong":[84],"correlation":[85],"with":[86],"overall":[88],"metrics":[90],"system,":[94],"validating":[95],"its":[96],"effectiveness":[97],"in":[98],"assessing":[99],"both":[100],"retrieval":[101],"answer":[103],"generation":[104],"capabilities.":[105,120],"By":[106],"ensuring":[107],"high-quality,":[108],"diverse,":[109],"difficulty-controlled":[111],"queries,":[112],"our":[113],"approach":[114],"enhances":[115],"evaluation":[117],"benchmarking":[119]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-14T00:00:00"}