{"id":"https://openalex.org/W7166814732","doi":"https://doi.org/10.18653/v1/2026.acl-long.432","title":"PAM: Enhancing General Alignment of Large Reasoning Models through Priority-Aware Metacognition","display_name":"PAM: Enhancing General Alignment of Large Reasoning Models through Priority-Aware Metacognition","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166814732","doi":"https://doi.org/10.18653/v1/2026.acl-long.432"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.432","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.432","pdf_url":"https://aclanthology.org/2026.acl-long.432.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.432.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139813457","display_name":"Zhihao Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210166345","display_name":"Intelligent Models (United States)","ror":"https://ror.org/05te6yt75","country_code":"US","type":"company","lineage":["https://openalex.org/I4210166345"]},{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zhihao Xu","raw_affiliation_strings":["Beijing Key Laboratory of Research on Large Models and Intelligent Governance","Gaoling School of Artificial Intelligence , Renmin University of China Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Research on Large Models and Intelligent Governance","institution_ids":["https://openalex.org/I4210166345"]},{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China Beijing , China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139822747","display_name":"Fuzhen Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuzhen Yang","raw_affiliation_strings":["Renmin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139725752","display_name":"Liang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Lin","raw_affiliation_strings":["Renmin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139791005","display_name":"Xiting Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210166345","display_name":"Intelligent Models (United States)","ror":"https://ror.org/05te6yt75","country_code":"US","type":"company","lineage":["https://openalex.org/I4210166345"]},{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Xiting Wang","raw_affiliation_strings":["Beijing Key Laboratory of Research on Large Models and Intelligent Governance","Gaoling School of Artificial Intelligence , Renmin University of China Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Research on Large Models and Intelligent Governance","institution_ids":["https://openalex.org/I4210166345"]},{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China Beijing , China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.7799541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9554","last_page":"9573"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.24459999799728394,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.24459999799728394,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.10540000349283218,"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":0.061400000005960464,"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/metacognition","display_name":"Metacognition","score":0.38989999890327454},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2924000024795532},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.2782000005245209},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.2671000063419342},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.2651999890804291}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6126999855041504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5544999837875366},{"id":"https://openalex.org/C118147538","wikidata":"https://www.wikidata.org/wiki/Q1126970","display_name":"Metacognition","level":3,"score":0.38989999890327454},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34150001406669617},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.432","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.432","pdf_url":"https://aclanthology.org/2026.acl-long.432.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.432","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.432","pdf_url":"https://aclanthology.org/2026.acl-long.432.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4876821041107178,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G3248486410","display_name":null,"funder_award_id":"U2436209","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4128466783","display_name":null,"funder_award_id":"92470205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6750762792","display_name":null,"funder_award_id":"62476279","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322499","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166814732.pdf","grobid_xml":"https://content.openalex.org/works/W7166814732.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2],"Large":[3],"Reasoning":[4],"Models":[5],"(LRMs)":[6],"have":[7],"showcased":[8],"strong":[9],"performance":[10,154],"across":[11],"various":[12],"reasoning":[13,25],"tasks":[14],"by":[15,37,155],"leveraging":[16],"System-2":[17,59],"thinking":[18,105],"capabilities.However,":[19],"existing":[20],"studies":[21],"indicate":[22],"that":[23,47,116,130],"this":[24,61],"ability":[26],"alone":[27],"does":[28],"not":[29],"reliably":[30],"transfer":[31],"to":[32,55,72,98],"the":[33,70,75,86,103,137,141,159],"general":[34,151],"alignment":[35,87,153],"domain.Inspired":[36],"cognitive":[38],"science":[39],"and":[40,90,101,126,161],"how":[41],"humans":[42],"solve":[43],"tasks,":[44],"we":[45,63],"argue":[46],"LRMs":[48],"must":[49],"be":[50],"equipped":[51],"with":[52],"metacognitive":[53,96,119],"knowledge":[54,97,120],"fully":[56],"utilize":[57],"their":[58],"capabilities.In":[60],"paper,":[62],"propose":[64],"PRIORITY-AWARE":[65],"METACOGNITION":[66],"(PAM),":[67],"which":[68],"guides":[69],"model":[71],"first":[73],"identify":[74],"top-level":[76],"human":[77],"preference":[78],"(e.g.,":[79],"harmlessness)":[80],"as":[81],"a":[82,110,113,127],"means":[83],"of":[84,95,139],"understanding":[85],"task's":[88],"nature,":[89],"then":[91],"apply":[92],"other":[93],"kinds":[94],"better":[99],"monitor":[100],"regulate":[102],"model's":[104],"process.We":[106],"implement":[107],"PAM":[108,145],"via":[109],"two-stage":[111],"pipeline:":[112],"cold-start":[114],"phase":[115,129],"collects":[117],"structured":[118],"based":[121],"on":[122,158],"Flavell's":[123],"theoretical":[124],"framework,":[125],"preference-optimization":[128],"further":[131],"reinforces":[132],"such":[133],"metacognition.Extensive":[134],"experiments":[135],"validate":[136],"effectiveness":[138],"PAM.Under":[140],"same":[142],"training":[143],"pipelines,":[144],"consistently":[146],"yields":[147],"higher":[148],"performance,":[149],"improving":[150],"domain":[152],"~10":[156],"points":[157],"helpfulness":[160],"harmless":[162],"benchmarks.Code":[163],"is":[164],"available":[165],"at":[166],"https://anonymous.4open.science/r/PAM-":[167],"8B42.":[168]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-07-02T00:00:00"}