{"id":"https://openalex.org/W4412888299","doi":"https://doi.org/10.18653/v1/2025.findings-acl.587","title":"RASPberry: Retrieval-Augmented Monte Carlo Tree Self-Play with Reasoning Consistency for Multi-Hop Question Answering","display_name":"RASPberry: Retrieval-Augmented Monte Carlo Tree Self-Play with Reasoning Consistency for Multi-Hop Question Answering","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888299","doi":"https://doi.org/10.18653/v1/2025.findings-acl.587"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.587","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.587","pdf_url":"https://aclanthology.org/2025.findings-acl.587.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.587.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108772020","display_name":"Baixuan Li","orcid":"https://orcid.org/0009-0007-8560-5875"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baixuan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033888089","display_name":"Yunlong Fan","orcid":"https://orcid.org/0000-0002-5027-3686"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunlong Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069605427","display_name":"Tianyi Ma","orcid":"https://orcid.org/0000-0001-6057-9825"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyi Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000651580","display_name":"Miao Gao","orcid":"https://orcid.org/0000-0002-5711-9382"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miao Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110994338","display_name":"Chuanqi Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuanqi Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056485034","display_name":"Zhiqiang Gao","orcid":"https://orcid.org/0000-0001-7381-9349"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiqiang Gao","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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11258","last_page":"11276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9976000189781189,"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":0.9976000189781189,"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":0.9740999937057495,"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/T12031","display_name":"Speech and dialogue systems","score":0.9650999903678894,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6800909042358398},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.5804827809333801},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5772468447685242},{"id":"https://openalex.org/keywords/hop","display_name":"Hop (telecommunications)","score":0.5444449782371521},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5409001708030701},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48421335220336914},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.45152536034584045},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.4127190113067627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.358122855424881},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17507880926132202},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16706758737564087},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.06788316369056702},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.06335461139678955}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6800909042358398},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.5804827809333801},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5772468447685242},{"id":"https://openalex.org/C25906391","wikidata":"https://www.wikidata.org/wiki/Q1432381","display_name":"Hop (telecommunications)","level":2,"score":0.5444449782371521},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5409001708030701},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48421335220336914},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.45152536034584045},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.4127190113067627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.358122855424881},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17507880926132202},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16706758737564087},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.06788316369056702},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.06335461139678955}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.587","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.587","pdf_url":"https://aclanthology.org/2025.findings-acl.587.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"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.587","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.587","pdf_url":"https://aclanthology.org/2025.findings-acl.587.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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888299.pdf","grobid_xml":"https://content.openalex.org/works/W4412888299.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2117210722","https://openalex.org/W2571592646","https://openalex.org/W2589759689","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W4247855592"],"abstract_inverted_index":{"Complex":[0],"multi-hop":[1],"question":[2],"answering":[3],"requires":[4],"large":[5],"language":[6],"models":[7],"(LLMs)":[8],"not":[9],"only":[10],"to":[11,17,25,37,53,99,120],"retrieve":[12],"external":[13],"knowledge":[14],"but":[15],"also":[16],"reason":[18],"over":[19],"the":[20,28,40,55,122,125,136],"retrieved":[21],"information":[22],"in":[23],"order":[24],"arrive":[26],"at":[27,150],"final":[29],"solution.This":[30],"involves":[31],"two":[32,137],"key":[33],"challenges:":[34],"(i)":[35],"how":[36,52],"effectively":[38,134],"explore":[39],"solution":[41,48,57,60,109],"space":[42,110],"and":[43,50,112],"generate":[44],"more":[45,72,93,142],"potentially":[46],"correct":[47],"candidates,":[49,61],"(ii)":[51],"select":[54],"optimal":[56,126],"from":[58],"multiple":[59],"both":[62],"of":[63,117,124],"which":[64,90],"require":[65],"a":[66,71,92],"training-free":[67],"approach":[68],"without":[69],"introducing":[70],"powerful":[73],"teacher":[74],"model.To":[75],"address":[76],"these":[77],"challenges,":[78],"we":[79],"propose":[80],"Retrieval-Augmented":[81],"Monte":[82,103],"Carlo":[83,104],"Tree":[84,105],"Self-Play":[85],"with":[86],"Reasoning":[87],"Consistency":[88],"(RASPberry),":[89],"introduces":[91],"flexible":[94],"action-level":[95],"sampling":[96],"granularity":[97],"compared":[98],"existing":[100],"methods,":[101],"leverages":[102],"Search":[106],"for":[107],"efficient":[108,143],"exploration,":[111],"utilizes":[113],"an":[114],"enhanced":[115],"version":[116],"reasoning":[118],"consistency":[119],"guide":[121],"selection":[123],"solution.Experimental":[127],"results":[128],"demonstrate":[129],"that":[130],"our":[131],"proposed":[132],"RASPberry":[133],"tackles":[135],"challenges":[138],"outlined":[139],"above,":[140],"achieving":[141],"RAG":[144],"inferencetime":[145],"scaling.Our":[146],"code":[147],"is":[148],"available":[149],"https:":[151],"//github.com/BaixuanLi/RASPberry.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}