{"id":"https://openalex.org/W4412888430","doi":"https://doi.org/10.18653/v1/2025.findings-acl.388","title":"Boosting Policy and Process Reward Models with Monte Carlo Tree Search in Open-Domain QA","display_name":"Boosting Policy and Process Reward Models with Monte Carlo Tree Search in Open-Domain QA","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888430","doi":"https://doi.org/10.18653/v1/2025.findings-acl.388"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.388","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.388","pdf_url":"https://aclanthology.org/2025.findings-acl.388.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.388.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044330945","display_name":"Chi-Min Chan","orcid":"https://orcid.org/0009-0006-0218-3412"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chi-Min Chan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002321609","display_name":"Chunpu Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunpu Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023017024","display_name":"Junqi Zhu","orcid":"https://orcid.org/0000-0001-9135-0505"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junqi Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010983432","display_name":"Jiaming Ji","orcid":"https://orcid.org/0000-0002-3769-2077"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaming Ji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Donghai Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Donghai Hong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114139822","display_name":"Pengcheng Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengcheng Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000483812","display_name":"Chunyang Jiang","orcid":"https://orcid.org/0000-0003-2211-6736"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunyang Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100731638","display_name":"Zhen Ye","orcid":"https://orcid.org/0009-0007-0687-9879"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhen Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025046910","display_name":"Yaodong Yang","orcid":"https://orcid.org/0000-0002-1707-0633"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaodong Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021255269","display_name":"Sirui Han","orcid":"https://orcid.org/0000-0001-7303-0671"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sirui Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5045081171","display_name":"Yike Guo","orcid":"https://orcid.org/0000-0002-3075-2161"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yike Guo","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":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7433","last_page":"7451"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11801","display_name":"Reservoir Engineering and Simulation Methods","score":0.8816999793052673,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/T11801","display_name":"Reservoir Engineering and Simulation Methods","score":0.8816999793052673,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.8780999779701233,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.8324000239372253,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.7870153784751892},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.657627284526825},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6552382111549377},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.5792130827903748},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4641626477241516},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44685086607933044},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42995569109916687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4062023162841797},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.3385559916496277},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1746336817741394},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14199396967887878}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7870153784751892},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.657627284526825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6552382111549377},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.5792130827903748},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4641626477241516},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44685086607933044},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42995569109916687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4062023162841797},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3385559916496277},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1746336817741394},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14199396967887878},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.388","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.388","pdf_url":"https://aclanthology.org/2025.findings-acl.388.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-168705","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-168705","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.388","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.388","pdf_url":"https://aclanthology.org/2025.findings-acl.388.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1142957533","display_name":null,"funder_award_id":"R9911","funder_id":"https://openalex.org/F4320323537","funder_display_name":"Hong Kong University of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320323537","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888430.pdf","grobid_xml":"https://content.openalex.org/works/W4412888430.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W2147697413","https://openalex.org/W2154063878","https://openalex.org/W4231274751","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W3082059448","https://openalex.org/W4313640622"],"abstract_inverted_index":{"Chi-Min":[0],"Chan,":[1],"Chunpu":[2],"Xu,":[3],"Junqi":[4],"Zhu,":[5],"Jiaming":[6],"Ji,":[7],"Donghai":[8],"Hong,":[9],"Pengcheng":[10],"Wen,":[11],"Chunyang":[12],"Jiang,":[13],"Zhen":[14],"Ye,":[15],"Yaodong":[16],"Yang,":[17],"Wei":[18],"Xue,":[19],"Sirui":[20],"Han,":[21],"Yike":[22],"Guo.":[23],"Findings":[24],"of":[25],"the":[26],"Association":[27],"for":[28],"Computational":[29],"Linguistics:":[30],"ACL":[31],"2025.":[32,33]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}