{"id":"https://openalex.org/W7224586278","doi":"https://doi.org/10.18653/2026.emnlp-main.1379","title":"PROBE: Prospective Retrieval with Oracle-Based End-Goal Distillation for Multi-Hop Question Answering","display_name":"PROBE: Prospective Retrieval with Oracle-Based End-Goal Distillation for Multi-Hop Question Answering","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7224586278","doi":"https://doi.org/10.18653/2026.emnlp-main.1379"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.1379","doi":"https://doi.org/10.18653/2026.emnlp-main.1379","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1379","pdf_url":"https://aclanthology.org/2026.emnlp-main.1379.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.emnlp-main.1379.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122274189","display_name":"Xu Lu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Lu","raw_affiliation_strings":["School of Software Technology , Zhejiang University","State Key Laboratory of Blockchain and Data Security , Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Technology , Zhejiang University","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"State Key Laboratory of Blockchain and Data Security , Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114091239","display_name":"Zhengqing Zang","orcid":"https://orcid.org/0009-0008-7904-9312","observed_orcids":["https://orcid.org/0009-0008-7904-9312"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqing Zang","raw_affiliation_strings":["State Key Laboratory of Blockchain and Data Security , Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Blockchain and Data Security , Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054102645","display_name":"Binhui Yao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binhui Yao","raw_affiliation_strings":["School of Software Technology , Zhejiang University","State Key Laboratory of Blockchain and Data Security , Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Technology , Zhejiang University","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"State Key Laboratory of Blockchain and Data Security , Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160107888","display_name":"Luwei Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210153393","display_name":"Geely (China)","ror":"https://ror.org/0446d5v35","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210153393"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luwei Yang","raw_affiliation_strings":["Zhejiang Geely Holding Group Co. , Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Geely Holding Group Co. , Ltd","institution_ids":["https://openalex.org/I4210153393"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102020261","display_name":"Ruimin Chen","orcid":"https://orcid.org/0000-0002-4758-5953","observed_orcids":["https://orcid.org/0000-0002-4758-5953"]},"institutions":[{"id":"https://openalex.org/I4210153393","display_name":"Geely (China)","ror":"https://ror.org/0446d5v35","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210153393"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruimin Chen","raw_affiliation_strings":["Zhejiang Geely Holding Group Co. , Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Geely Holding Group Co. , Ltd","institution_ids":["https://openalex.org/I4210153393"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160103237","display_name":"Zeng Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210153393","display_name":"Geely (China)","ror":"https://ror.org/0446d5v35","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210153393"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeng Wang","raw_affiliation_strings":["Zhejiang Geely Holding Group Co. , Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Geely Holding Group Co. , Ltd","institution_ids":["https://openalex.org/I4210153393"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100765044","display_name":"Haobo Wang","orcid":"https://orcid.org/0000-0001-7952-6950","observed_orcids":["https://orcid.org/0000-0001-7952-6950"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haobo Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"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":0.89955311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"31494","last_page":"31515"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9315999746322632,"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":0.9315999746322632,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.029899999499320984,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.012500000186264515,"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":0.9860000014305115},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.7289999723434448},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.7099999785423279},{"id":"https://openalex.org/keywords/question-answering","display_name":"question answering","score":0.3880000114440918}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7293000221252441},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.590399980545044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47929999232292175},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45730000734329224},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3869999945163727},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.3862000107765198},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/2026.emnlp-main.1379","doi":"https://doi.org/10.18653/2026.emnlp-main.1379","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1379","pdf_url":"https://aclanthology.org/2026.emnlp-main.1379.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/2026.emnlp-main.1379","doi":"https://doi.org/10.18653/2026.emnlp-main.1379","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1379","pdf_url":"https://aclanthology.org/2026.emnlp-main.1379.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322927","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224586278.pdf","grobid_xml":"https://content.openalex.org/works/W7224586278.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4404782834","https://openalex.org/W7223695688","https://openalex.org/W6976617253","https://openalex.org/W2939380783","https://openalex.org/W4401043457","https://openalex.org/W4399717458","https://openalex.org/W7224534329","https://openalex.org/W2971096647","https://openalex.org/W7131883798","https://openalex.org/W4416034106"],"abstract_inverted_index":{"Multi-hop":[0],"question":[1],"answering":[2],"(MHQA)":[3],"requires":[4],"models":[5],"to":[6,29,55],"retrieve":[7],"and":[8,58,97,133],"reason":[9],"over":[10,46,136],"evidence":[11,66],"distributed":[12],"across":[13],"multiple":[14],"documents.However,":[15],"training":[16,154],"dense":[17,79],"retrievers":[18,80],"for":[19,31,43,81],"MHQA":[20,82,124],"remains":[21],"challenging":[22],"because":[23],"labeled":[24],"querydocument":[25,87],"pairs":[26],"are":[27],"difficult":[28],"obtain":[30],"the":[32,90,112,153,157],"evolving":[33],"intermediate":[34],"queries":[35,47],"in":[36],"multi-hop":[37],"reasoning.Recent":[38],"approaches":[39],"use":[40],"LLM":[41],"likelihoods":[42],"step-wise":[44],"supervision":[45,60,117],"conditioned":[48],"on":[49,122],"accumulated":[50],"evidence,":[51],"which":[52],"anchors":[53],"retrieval":[54,132],"known":[56],"facts":[57],"biases":[59],"toward":[61],"answer-bearing":[62],"documents,":[63],"leaving":[64],"bridging":[65],"undiscovered.To":[67],"address":[68],"this,":[69],"we":[70,106],"propose":[71],"PROBE":[72,128],"1":[73],",":[74],"a":[75,94,98],"framework":[76],"that":[77,101,127],"optimizes":[78],"without":[83,118],"requiring":[84],"manually":[85],"annotated":[86],"pairs.It":[88],"decouples":[89],"reasoning":[91],"state":[92],"into":[93],"factual":[95],"summary":[96],"prospective":[99],"query":[100],"anticipates":[102],"missing":[103],"information.For":[104],"training,":[105],"transfer":[107],"cross-encoder":[108],"signals":[109],"only":[110,149],"at":[111],"final":[113],"hop,":[114],"providing":[115],"trajectorylevel":[116],"penalizing":[119],"early":[120],"exploration.Experiments":[121],"three":[123],"benchmarks":[125],"show":[126],"consistently":[129],"improves":[130],"both":[131],"QA":[134],"performance":[135],"strong":[137],"iterative":[138],"baselines,":[139],"achieving":[140],"an":[141],"average":[142],"gain":[143],"of":[144,152,156],"5.7":[145],"points":[146],"while":[147],"using":[148],"about":[150],"5%":[151],"data":[155],"prior":[158],"method.":[159]},"counts_by_year":[],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2026-10-30T00:00:00"}