{"id":"https://openalex.org/W7207541998","doi":"https://doi.org/10.18653/2026.emnlp-main.1667","title":"PRO-Step: Step-level Process Reward Optimization for Retrieval-Augmented Generation","display_name":"PRO-Step: Step-level Process Reward Optimization for Retrieval-Augmented Generation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7207541998","doi":"https://doi.org/10.18653/2026.emnlp-main.1667"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.1667","doi":"https://doi.org/10.18653/2026.emnlp-main.1667","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1667","pdf_url":"https://aclanthology.org/2026.emnlp-main.1667.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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.emnlp-main.1667.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140604000","display_name":"Minkeon Kim","orcid":"https://orcid.org/0009-0006-8248-1785","observed_orcids":["https://orcid.org/0009-0006-8248-1785"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"MinKeon Kim","raw_affiliation_strings":["Department of Applied Artificial Intelligence ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Artificial Intelligence ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133247571","display_name":"Namjun Lee","orcid":"https://orcid.org/0009-0006-6545-6422","observed_orcids":["https://orcid.org/0009-0006-6545-6422"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Namjun Lee","raw_affiliation_strings":["Department of Applied Artificial Intelligence ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Artificial Intelligence ,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100652679","display_name":"Jaekwang Kim","orcid":"https://orcid.org/0000-0001-5174-0074","observed_orcids":["https://orcid.org/0000-0001-5174-0074"]},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaekwang Kim","raw_affiliation_strings":["Convergence Program for Social Innovation , Sungkyunkwan University , Seoul , South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Convergence Program for Social Innovation , Sungkyunkwan University , Seoul , South Korea","institution_ids":["https://openalex.org/I848706"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.7036679,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"37904","last_page":"37925"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8672000169754028,"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":0.8672000169754028,"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":0.09189999848604202,"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":0.011599999852478504,"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/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9980000257492065},{"id":"https://openalex.org/keywords/multi-hop-reasoning","display_name":"multi-hop reasoning","score":0.796999990940094},{"id":"https://openalex.org/keywords/error-propagation","display_name":"error propagation","score":0.9319999814033508},{"id":"https://openalex.org/keywords/direct-preference-optimization","display_name":"direct preference optimization","score":0.9070000052452087},{"id":"https://openalex.org/keywords/logical-validity","display_name":"logical validity","score":0.5270000100135803},{"id":"https://openalex.org/keywords/preference-pairs","display_name":"preference pairs","score":0.4099999964237213},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6520000100135803}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.7475000023841858},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7145000100135803},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5665000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5609999895095825},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5266000032424927},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5151000022888184},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.47350001335144043},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33869999647140503},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C156201811","wikidata":"https://www.wikidata.org/wiki/Q5418360","display_name":"Evidential reasoning approach","level":4,"score":0.2842000126838684},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.28290000557899475},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.260699987411499}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.emnlp-main.1667","doi":"https://doi.org/10.18653/2026.emnlp-main.1667","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1667","pdf_url":"https://aclanthology.org/2026.emnlp-main.1667.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"},{"id":"pmh:oai:arXiv.org:2609.01658","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.01658","pdf_url":"https://arxiv.org/pdf/2609.01658","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.2609.01658","doi":"https://doi.org/10.48550/arxiv.2609.01658","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.01658","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:10.18653/2026.emnlp-main.1667","doi":"https://doi.org/10.18653/2026.emnlp-main.1667","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1667","pdf_url":"https://aclanthology.org/2026.emnlp-main.1667.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":[{"id":"https://openalex.org/G1428394818","display_name":null,"funder_award_id":"RS- 2024-00459638","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G1977249509","display_name":null,"funder_award_id":"RS-2023-00259497","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G2514582570","display_name":null,"funder_award_id":"IITP-2026-RS-2023-00254129","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G2652541173","display_name":null,"funder_award_id":"RS-2023-00259497","funder_id":"https://openalex.org/F4320321378","funder_display_name":"Sungkyunkwan University"},{"id":"https://openalex.org/G314908243","display_name":null,"funder_award_id":"RS-2024-00346737","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G3812690899","display_name":null,"funder_award_id":"RS-2023","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4256929933","display_name":null,"funder_award_id":"IITP-2026-RS-2023-00259497","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4288452366","display_name":null,"funder_award_id":"RS-2023-00254129","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G440996017","display_name":null,"funder_award_id":"RS-2024-00459638","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G5093466393","display_name":null,"funder_award_id":"RS-2023-00254129","funder_id":"https://openalex.org/F4320321378","funder_display_name":"Sungkyunkwan University"},{"id":"https://openalex.org/G5593258703","display_name":null,"funder_award_id":"IITP-2026-RS-2023-00254129","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G6500653232","display_name":null,"funder_award_id":"RS-2023-00254129","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321378","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7207541998.pdf","grobid_xml":"https://content.openalex.org/works/W7207541998.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7126249609","https://openalex.org/W4416290984","https://openalex.org/W4412377895","https://openalex.org/W4416034879","https://openalex.org/W7161129374","https://openalex.org/W4415413158","https://openalex.org/W6967136336","https://openalex.org/W6891757201","https://openalex.org/W4416035522","https://openalex.org/W4412889842"],"abstract_inverted_index":{"Retrieval-Augmented":[0],"Generation":[1],"enhances":[2],"Large":[3],"Language":[4],"Models":[5],"by":[6],"grounding":[7,77],"responses":[8],"in":[9,68],"external":[10],"knowledge,":[11],"but":[12],"multi-hop":[13,118],"reasoning":[14,38],"remains":[15],"vulnerable":[16],"to":[17,97],"error":[18],"propagation,":[19],"where":[20,59],"early":[21],"retrieval":[22,36,61],"failures":[23],"confound":[24],"subsequent":[25],"steps.Standard":[26],"outcome-based":[27],"optimization":[28],"only":[29],"rewards":[30],"the":[31,53,64,109,125],"final":[32,54],"answer,":[33,55],"leaving":[34],"intermediate":[35],"and":[37,75,107,129,135],"errors":[39],"undetected.While":[40],"existing":[41],"process-based":[42],"methods":[43],"introduce":[44,81],"step-level":[45,112],"signals,":[46],"they":[47],"still":[48],"score":[49],"each":[50,79],"step":[51],"against":[52,104],"rewarding":[56],"spurious":[57],"successes":[58],"flawed":[60,105],"coincidentally":[62],"produces":[63],"correct":[65],"answer.Steplevel":[66],"supervision":[67],"RAG":[69],"requires":[70],"evaluating":[71],"both":[72,90],"logical":[73],"validity":[74],"evidential":[76],"at":[78,141],"step.We":[80],"PRO-STEP:":[82],"we":[83],"train":[84],"a":[85],"generative":[86],"PRM":[87],"that":[88,122],"evaluates":[89],"dimensions,":[91],"employ":[92],"PRM-guided":[93],"value":[94],"tree":[95],"search":[96],"construct":[98],"preference":[99],"pairs":[100],"contrasting":[101],"valid":[102],"steps":[103],"ones,":[106],"optimize":[108],"policy":[110],"via":[111],"Direct":[113],"Preference":[114],"Optimization.Experiments":[115],"on":[116],"singleand":[117],"QA":[119],"datasets":[120],"demonstrate":[121],"PRO-STEP":[123],"achieves":[124],"best":[126],"average":[127],"EM":[128],"F1":[130],"across":[131],"five":[132],"benchmarks.Code,":[133],"models,":[134],"training":[136],"data":[137],"are":[138],"publicly":[139],"available":[140],"https://github.com/keemminnke/PRO-Step.":[142]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-09-04T00:00:00"}