{"id":"https://openalex.org/W7138408078","doi":"https://doi.org/10.1609/aaai.v40i36.40306","title":"W2S-AlignTree: Weak-to-Strong Inference-Time Alignment for Large Language Models via Monte Carlo Tree Search","display_name":"W2S-AlignTree: Weak-to-Strong Inference-Time Alignment for Large Language Models via Monte Carlo Tree Search","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138408078","doi":"https://doi.org/10.1609/aaai.v40i36.40306"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i36.40306","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i36.40306","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40306/44267","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40306/44267","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101528527","display_name":"Zhenyu Ding","orcid":"https://orcid.org/0000-0001-7014-186X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenyu Ding","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129678938","display_name":"Yuhao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Wang","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056771892","display_name":"Tengyue Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tengyue Xiao","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129748637","display_name":"Haoying Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoying Wang","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129652320","display_name":"Guojun Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guojun Ma","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016314811","display_name":"Mingyang Wan","orcid":"https://orcid.org/0000-0002-1536-3643"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyang Wan","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055140272","display_name":"Caigui Jiang","orcid":"https://orcid.org/0000-0002-1342-4094"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Caigui Jiang","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129724870","display_name":"Ning Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Ding","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101528527"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.54541109,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"36","first_page":"30521","last_page":"30529"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3603000044822693,"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":0.3603000044822693,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.1875,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0568000003695488,"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/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.7706000208854675},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6700000166893005},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.5898000001907349},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5616999864578247},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5353000164031982},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.49900001287460327},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4307999908924103},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4244999885559082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7989000082015991},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.7706000208854675},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6700000166893005},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.5898000001907349},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5616999864578247},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5514000058174133},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5353000164031982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5167999863624573},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.49900001287460327},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.39430001378059387},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3806999921798706},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.2824999988079071},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.25780001282691956},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2558000087738037},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2538999915122986},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C207024777","wikidata":"https://www.wikidata.org/wiki/Q621673","display_name":"Search tree","level":3,"score":0.2526000142097473},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C2775935494","wikidata":"https://www.wikidata.org/wiki/Q741964","display_name":"Search and rescue","level":3,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i36.40306","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i36.40306","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40306/44267","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i36.40306","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i36.40306","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40306/44267","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138408078.pdf","grobid_xml":"https://content.openalex.org/works/W7138408078.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"demonstrate":[4],"impressive":[5],"capabilities,":[6],"yet":[7],"their":[8],"outputs":[9],"often":[10],"suffer":[11],"from":[12,36,174],"misalignment":[13],"with":[14,88],"human":[15],"preferences":[16],"due":[17],"to":[18,176],"the":[19,89,94,170,184],"inadequacy":[20],"of":[21,27,172,181],"weak":[22,114],"supervision":[23,45],"and":[24,46,64,122,145,158],"a":[25,74,108,178],"lack":[26],"fine-grained":[28,130],"control.":[29],"Training-time":[30],"alignment":[31,66,78,100,120],"methods":[32],"like":[33],"Reinforcement":[34],"Learning":[35],"Human":[37],"Feedback":[38],"(RLHF)":[39],"face":[40],"prohibitive":[41],"costs":[42],"in":[43,147],"expert":[44],"inherent":[47],"scalability":[48],"limitations,":[49],"offering":[50],"limited":[51],"dynamic":[52],"control":[53],"during":[54,132],"inference.":[55],"Consequently,":[56],"there":[57],"is":[58],"an":[59,102,124],"urgent":[60],"need":[61],"for":[62,93],"scalable":[63],"adaptable":[65],"mechanisms.":[67],"To":[68],"address":[69],"this,":[70],"we":[71],"propose":[72],"W2S-AlignTree,":[73],"pioneering":[75],"plug-and-play":[76],"inference-time":[77],"framework":[79],"that":[80,161],"synergistically":[81],"combines":[82],"Monte":[83],"Carlo":[84],"Tree":[85],"Search":[86],"(MCTS)":[87],"Weak-to-Strong":[90],"Generalization":[91],"paradigm":[92],"first":[95],"time.":[96],"W2S-AlignTree":[97,128,162,168],"formulates":[98],"LLM":[99],"as":[101,119],"optimal":[103],"heuristic":[104],"search":[105,110,150],"problem":[106],"within":[107],"generative":[109],"tree.":[111],"By":[112],"leveraging":[113],"model's":[115,134],"real-time,":[116],"step-level":[117],"signals":[118],"proxies":[121],"introducing":[123],"Entropy-Aware":[125],"exploration":[126,144],"mechanism,":[127],"enables":[129],"guidance":[131],"strong":[133,165],"generation":[135,149],"without":[136],"modifying":[137],"its":[138],"parameters.":[139],"The":[140],"approach":[141],"dynamically":[142],"balances":[143],"exploitation":[146],"high-dimensional":[148],"trees.":[151],"Experiments":[152],"across":[153],"controlled":[154],"sentiment":[155],"generation,":[156],"summarization,":[157],"instruction-following":[159],"show":[160],"consistently":[163],"outperforms":[164],"baselines.":[166],"Notably,":[167],"raises":[169],"performance":[171],"Llama3-8B":[173],"1.89":[175],"2.19,":[177],"relative":[179],"improvement":[180],"15.9%":[182],"on":[183],"summarization":[185],"task.":[186]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-18T00:00:00"}