{"id":"https://openalex.org/W4412945162","doi":"https://doi.org/10.18653/v1/2025.acl-long.1190","title":"FastMCTS: A Simple Sampling Strategy for Data Synthesis","display_name":"FastMCTS: A Simple Sampling Strategy for Data Synthesis","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945162","doi":"https://doi.org/10.18653/v1/2025.acl-long.1190"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1190","doi":"https://doi.org/10.18653/v1/2025.acl-long.1190","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1190","pdf_url":"https://aclanthology.org/2025.acl-long.1190.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd 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":"bronze","oa_url":"https://aclanthology.org/2025.acl-long.1190.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034347070","display_name":"Peiji Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiji Li","raw_affiliation_strings":["Fudan University","Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kai Lv","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Lv","raw_affiliation_strings":["Fudan University","Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061237050","display_name":"Yunfan Shao","orcid":"https://orcid.org/0000-0002-2770-7036","observed_orcids":["https://orcid.org/0000-0002-2770-7036"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunfan Shao","raw_affiliation_strings":["Fudan University","Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022014664","display_name":"Ye Ma","orcid":"https://orcid.org/0000-0001-5999-4650","observed_orcids":["https://orcid.org/0000-0001-5999-4650","https://orcid.org/0009-0007-4052-8618"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichuan Ma","raw_affiliation_strings":["Fudan University","Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086682667","display_name":"Linyang Li","orcid":"https://orcid.org/0000-0003-1056-6406","observed_orcids":["https://orcid.org/0000-0003-1056-6406","https://orcid.org/0000-0002-9757-7345"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linyang Li","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoqing Zheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqing Zheng","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044665993","display_name":"Xipeng Qiu","orcid":"https://orcid.org/0000-0001-7163-5247","observed_orcids":["https://orcid.org/0000-0001-7163-5247"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xipeng Qiu","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":null,"display_name":"Qipeng Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qipeng Guo","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]}],"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":0.24552987,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24405","last_page":"24422"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.5088000297546387,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.5088000297546387,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.13760000467300415,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.03999999910593033,"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/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.906000018119812},{"id":"https://openalex.org/keywords/data-synthesis","display_name":"data synthesis","score":0.8379999995231628},{"id":"https://openalex.org/keywords/sampling-strategy","display_name":"sampling strategy","score":0.8109999895095825},{"id":"https://openalex.org/keywords/synthetic-data-generation","display_name":"synthetic data generation","score":0.8550000190734863}],"concepts":[{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6988059878349304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6813760995864868},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4840533137321472},{"id":"https://openalex.org/C20353970","wikidata":"https://www.wikidata.org/wiki/Q1056998","display_name":"Simple random sample","level":3,"score":0.41792812943458557},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0758582353591919},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1190","doi":"https://doi.org/10.18653/v1/2025.acl-long.1190","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1190","pdf_url":"https://aclanthology.org/2025.acl-long.1190.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.11476","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.11476","pdf_url":"https://arxiv.org/pdf/2502.11476","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2502.11476","doi":"https://doi.org/10.48550/arxiv.2502.11476","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.11476","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.1190","doi":"https://doi.org/10.18653/v1/2025.acl-long.1190","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1190","pdf_url":"https://aclanthology.org/2025.acl-long.1190.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd 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/G1817111062","display_name":null,"funder_award_id":"2022ZD0160102","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321851","display_name":"Fudan University","ror":"https://ror.org/013q1eq08"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945162.pdf","grobid_xml":"https://content.openalex.org/works/W4412945162.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7133341380","https://openalex.org/W7197050206","https://openalex.org/W4402712382","https://openalex.org/W7140345869","https://openalex.org/W7202406069","https://openalex.org/W7133235186","https://openalex.org/W4416117513","https://openalex.org/W6929447323","https://openalex.org/W4416445771","https://openalex.org/W4412888300"],"abstract_inverted_index":{"Synthetic":[0],"high-quality":[1,144],"multi-step":[2,63],"reasoning":[3,64,85,95,145],"data":[4,47,112,118,125],"can":[5],"significantly":[6],"enhance":[7],"the":[8,102],"performance":[9],"of":[10,37,76,104],"large":[11],"language":[12],"models":[13,114],"on":[14,21,80,116,122],"various":[15],"tasks.However,":[16],"most":[17],"existing":[18],"methods":[19],"rely":[20],"rejection":[22,99,123],"sampling,":[23],"which":[24],"generates":[25,90],"trajectories":[26],"independently":[27],"and":[28,32,70,83,139],"suffers":[29],"from":[30],"inefficiency":[31],"imbalanced":[33],"sampling":[34,60,73,100,124,133],"across":[35,74,128],"problems":[36,75],"varying":[38],"difficulty.In":[39],"this":[40],"work,":[41],"we":[42],"introduce":[43],"FastM-CTS,":[44],"an":[45],"innovative":[46],"synthesis":[48],"strategy":[49],"inspired":[50],"by":[51,126],"Monte":[52],"Carlo":[53],"Tree":[54],"Search.FastMCTS":[55],"provides":[56],"a":[57,131,137],"more":[58,93],"efficient":[59,140],"method":[61],"for":[62,142],"data,":[65],"offering":[66],"step-level":[67],"evaluation":[68],"signals":[69],"promoting":[71],"balanced":[72],"different":[77],"difficulty":[78],"levels.Experiments":[79],"both":[81],"English":[82],"Chinese":[84],"datasets":[86],"demonstrate":[87],"that":[88],"FastMCTS":[89,135],"over":[91],"30%":[92],"correct":[94],"paths":[96],"compared":[97],"to":[98],"as":[101],"number":[103],"generated":[105],"tokens":[106],"scales":[107],"up.Furthermore,":[108],"under":[109],"comparable":[110],"synthetic":[111],"budgets,":[113],"trained":[115,121],"FastMCTS-generated":[117],"outperform":[119],"those":[120],"3.9%":[127],"multiple":[129],"benchmarks.As":[130],"lightweight":[132],"strategy,":[134],"offers":[136],"practical":[138],"alternative":[141],"synthesizing":[143],"data.Our":[146],"code":[147],"will":[148],"be":[149],"publicly":[150],"released.":[151]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2025-10-10T00:00:00"}