{"id":"https://openalex.org/W4415314060","doi":"https://doi.org/10.18653/v1/2026.acl-long.1295","title":"HopWeaver: Cross-Document Synthesis of High-Quality and Authentic Multi-Hop Questions","display_name":"HopWeaver: Cross-Document Synthesis of High-Quality and Authentic Multi-Hop Questions","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415314060","doi":"https://doi.org/10.18653/v1/2026.acl-long.1295"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1295","doi":"https://doi.org/10.18653/v1/2026.acl-long.1295","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1295","pdf_url":"https://aclanthology.org/2026.acl-long.1295.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.acl-long.1295.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhiyu Shen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyu Shen","raw_affiliation_strings":["School of Computer Science and Engineering , Sun Yat-sen University , Guangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Sun Yat-sen University , Guangzhou , China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiyuan Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiyuan Liu","raw_affiliation_strings":["School of Computer Science and Engineering , Sun Yat-sen University , Guangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Sun Yat-sen University , Guangzhou , China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yunhe Pang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhe Pang","raw_affiliation_strings":["School of Computer Science and Engineering , Sun Yat-sen University , Guangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Sun Yat-sen University , Guangzhou , China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101797069","display_name":"Yanghui Rao","orcid":"https://orcid.org/0000-0002-2887-8056","observed_orcids":["https://orcid.org/0000-0002-2887-8056"]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanghui Rao","raw_affiliation_strings":["School of Computer Science and Engineering , Sun Yat-sen University , Guangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Sun Yat-sen University , Guangzhou , China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072482402","display_name":"Fu Lee Wang","orcid":"https://orcid.org/0000-0002-3976-0053","observed_orcids":["https://orcid.org/0000-0002-3976-0053"]},"institutions":[{"id":"https://openalex.org/I8679417","display_name":"Hong Kong Metropolitan University","ror":"https://ror.org/0349bsm71","country_code":"HK","type":"education","lineage":["https://openalex.org/I8679417"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Fu Lee Wang","raw_affiliation_strings":["School of Science and Technology , Hong Kong Metropolitan University , Hong Kong SAR , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Science and Technology , Hong Kong Metropolitan University , Hong Kong SAR , China","institution_ids":["https://openalex.org/I8679417"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jianxing Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxing Yu","raw_affiliation_strings":["Key Laboratory of Sustainable Tourism Smart Assessment Technology , Ministry of Culture and Tourism , China","School of Artificial Intelligence , Sun Yat-sen University , Zhuhai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Sustainable Tourism Smart Assessment Technology , Ministry of Culture and Tourism , China","institution_ids":[]},{"raw_affiliation_string":"School of Artificial Intelligence , Sun Yat-sen University , Zhuhai , China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01111045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"28078","last_page":"28109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9634000062942505,"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":0.9634000062942505,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.02019999921321869,"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":0.008700000122189522,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multi-hop-question-answering","display_name":"multi-hop question answering","score":0.9710000157356262},{"id":"https://openalex.org/keywords/benchmark-generation","display_name":"benchmark generation","score":0.41499999165534973},{"id":"https://openalex.org/keywords/comparison-questions","display_name":"comparison questions","score":0.9890000224113464},{"id":"https://openalex.org/keywords/reasoning-paths","display_name":"reasoning paths","score":0.7369999885559082},{"id":"https://openalex.org/keywords/low-resource-domains","display_name":"low-resource domains","score":0.7630000114440918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7267000079154968},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6183000206947327},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.48019999265670776},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44929999113082886},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4018000066280365},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3336000144481659},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2964000105857849},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2782000005245209},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.26159998774528503}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1295","doi":"https://doi.org/10.18653/v1/2026.acl-long.1295","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1295","pdf_url":"https://aclanthology.org/2026.acl-long.1295.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.15087","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.15087","pdf_url":"https://arxiv.org/pdf/2505.15087","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,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2505.15087","doi":"https://doi.org/10.48550/arxiv.2505.15087","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.15087","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1295","doi":"https://doi.org/10.18653/v1/2026.acl-long.1295","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1295","pdf_url":"https://aclanthology.org/2026.acl-long.1295.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4915157000","display_name":null,"funder_award_id":"62372483","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5720687473","display_name":null,"funder_award_id":"62276279","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6139988440","display_name":null,"funder_award_id":"2024B1515020032","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415314060.pdf","grobid_xml":"https://content.openalex.org/works/W4415314060.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3190126809","https://openalex.org/W4399912759","https://openalex.org/W7102405943","https://openalex.org/W4416034980","https://openalex.org/W3115947671","https://openalex.org/W7165742659","https://openalex.org/W6891858697","https://openalex.org/W7172443246","https://openalex.org/W4405621431","https://openalex.org/W3093354052"],"abstract_inverted_index":{"Multi-Hop":[0],"Question":[1],"Answering":[2],"(MHQA)":[3],"is":[4,23,28,158],"crucial":[5],"for":[6,86,115,133,156],"evaluating":[7,87],"the":[8,47,88,95,116,141],"model's":[9],"capability":[10],"to":[11,76,103,139],"integrate":[12],"information":[13],"from":[14,125],"diverse":[15],"sources.However,":[16],"creating":[17],"extensive":[18,41],"and":[19,30,60,71,136],"high-quality":[20],"MHQA":[21],"datasets":[22,105],"challenging:":[24],"(i)":[25],"manual":[26,42],"annotation":[27],"expensive,":[29],"(ii)":[31],"current":[32],"synthesis":[33],"methods":[34],"often":[35],"produce":[36],"simplistic":[37],"questions":[38,54,62,97],"or":[39,100],"require":[40],"guidance.This":[43],"paper":[44],"introduces":[45],"HopWeaver,":[46],"first":[48],"cross-document":[49],"framework":[50,110],"synthesizing":[51],"authentic":[52,73],"multi-hop":[53,79,90],"without":[55],"human":[56],"intervention.HopWeaver":[57],"synthesizes":[58],"bridge":[59],"comparison":[61],"through":[63],"an":[64],"innovative":[65],"pipeline":[66],"that":[67,94],"identifies":[68],"complementary":[69],"documents":[70],"constructs":[72],"reasoning":[74,142],"paths":[75],"ensure":[77],"true":[78],"reasoning.We":[80],"further":[81],"present":[82],"a":[83,107,112],"comprehensive":[84],"system":[85],"synthesized":[89,96],"questions.Empirical":[91],"evaluations":[92],"demonstrate":[93],"achieve":[98],"comparable":[99],"superior":[101],"quality":[102],"human-annotated":[104],"at":[106],"lower":[108],"cost.Our":[109],"provides":[111],"valuable":[113],"tool":[114],"research":[117],"community:":[118],"it":[119],"can":[120],"automatically":[121],"generate":[122],"challenging":[123],"benchmarks":[124],"any":[126],"raw":[127],"corpus,":[128],"which":[129],"opens":[130],"new":[131],"avenues":[132],"both":[134],"evaluation":[135],"targeted":[137],"training":[138],"improve":[140],"capabilities":[143],"of":[144],"advanced":[145],"question":[146],"answering":[147],"models,":[148],"especially":[149],"in":[150],"domains":[151],"with":[152],"scarce":[153],"resources.The":[154],"code":[155],"HopWeaver":[157],"publicly":[159],"available":[160],"1":[161],".":[162]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2025-10-18T00:00:00"}