{"id":"https://openalex.org/W4411472182","doi":"https://doi.org/10.1109/jstsp.2025.3581101","title":"Leveraging Correctness-Based Learning for Efficient Reasoning via Automated Process Supervision","display_name":"Leveraging Correctness-Based Learning for Efficient Reasoning via Automated Process Supervision","publication_year":2025,"publication_date":"2025-06-20","ids":{"openalex":"https://openalex.org/W4411472182","doi":"https://doi.org/10.1109/jstsp.2025.3581101"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2025.3581101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2025.3581101","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yuxuan Yao","orcid":"https://orcid.org/0009-0009-3955-7272"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Yuxuan Yao","raw_affiliation_strings":["City University of Hong Kong, Hong Kong","City University of Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0009-3955-7272","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"City University of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443450","display_name":"Mingyang Liu","orcid":"https://orcid.org/0009-0005-5186-0590"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Mingyang Liu","raw_affiliation_strings":["City University of Hong Kong, Hong Kong","City University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"City University of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097955037","display_name":"Guanzhi Deng","orcid":"https://orcid.org/0009-0003-9557-5308"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Guanzhi Deng","raw_affiliation_strings":["City University of Hong Kong, Hong Kong","City University of Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0003-9557-5308","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"City University of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076640378","display_name":"Zengyan Liu","orcid":"https://orcid.org/0000-0003-3825-5474"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zengyan Liu","raw_affiliation_strings":["City University of Hong Kong, Hong Kong","City University of Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-3825-5474","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"City University of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001469325","display_name":"Dapeng Wu","orcid":"https://orcid.org/0000-0003-1755-0183"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dapeng Wu","raw_affiliation_strings":["City University of Hong Kong, Hong Kong","City University of Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-1755-0183","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"City University of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101206779","display_name":"Zhijiang Guo","orcid":"https://orcid.org/0000-0002-6232-5957"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijiang Guo","raw_affiliation_strings":["Huawei Noah’s Ark Lab, Shenzhen, China","Huawei Noah's Ark Lab, China"],"raw_orcid":"https://orcid.org/0000-0002-6232-5957","affiliations":[{"raw_affiliation_string":"Huawei Noah’s Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Han Wu","orcid":"https://orcid.org/0000-0002-8008-064X"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Wu","raw_affiliation_strings":["Huawei Noah’s Ark Lab, Shenzhen, China","Huawei Noah's Ark Lab, China"],"raw_orcid":"https://orcid.org/0000-0002-8008-064X","affiliations":[{"raw_affiliation_string":"Huawei Noah’s Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035185924","display_name":"Linqi Song","orcid":"https://orcid.org/0000-0003-2756-4984"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Linqi Song","raw_affiliation_strings":["City University of Hong Kong, Hong Kong","City University of Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-2756-4984","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"City University of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I168719708"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23569111,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"19","issue":"7","first_page":"1318","last_page":"1328"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.9979000091552734,"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"}},"topics":[{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.8243887424468994},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8060210943222046},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6990607976913452},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5460647344589233},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4415067434310913},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17642742395401}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.8243887424468994},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8060210943222046},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6990607976913452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5460647344589233},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4415067434310913},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17642742395401}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2025.3581101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2025.3581101","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3643945900","display_name":null,"funder_award_id":"62371411","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1965555277","https://openalex.org/W2786472750","https://openalex.org/W2909398625","https://openalex.org/W2962800603","https://openalex.org/W3027418681","https://openalex.org/W3159959439","https://openalex.org/W3170403598","https://openalex.org/W4384561707","https://openalex.org/W4385570481","https://openalex.org/W4385571645","https://openalex.org/W4385572146","https://openalex.org/W4385572830","https://openalex.org/W4385572965","https://openalex.org/W4389520255","https://openalex.org/W4390035079","https://openalex.org/W4392637287","https://openalex.org/W4393160302","https://openalex.org/W4396665924","https://openalex.org/W4402671689","https://openalex.org/W4404781903"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"exceptional":[6],"performance":[7,80],"across":[8],"various":[9],"tasks,":[10],"yet":[11],"they":[12],"still":[13],"face":[14],"limitations":[15],"such":[16,100],"as":[17,109],"hallucination,":[18],"unfaithful":[19],"reasoning,":[20],"and":[21,61],"toxic":[22],"content.":[23],"One":[24],"potential":[25],"approach":[26],"to":[27,32,90,119],"mitigate":[28],"these":[29],"issues":[30],"is":[31,88],"learn":[33],"from":[34,75],"human":[35,57],"feedback":[36],"or":[37],"external":[38,59],"tools.":[39],"In":[40,99],"this":[41],"paper,":[42],"we":[43,114],"introduce":[44],"an":[45,110],"intrinsic":[46],"self-correcting":[47],"reasoning":[48,71,79],"framework":[49],"for":[50,56],"LLMs":[51],"that":[52,92],"eliminates":[53],"the":[54,102,121,128],"need":[55],"input,":[58],"tools,":[60],"handcrafted":[62],"prompts.":[63],"Our":[64],"proposed":[65],"framework,":[66],"based":[67],"on":[68,83],"a":[69],"multi-step":[70],"paradigm":[72],"called":[73],"Learning":[74],"Correctness":[76],"(LECO),":[77],"enhances":[78],"without":[81],"relying":[82],"error-based":[84],"learning.":[85],"However,":[86],"it":[87],"important":[89],"note":[91],"model":[93,106],"logits":[94],"are":[95],"not":[96],"always":[97],"available.":[98],"cases,":[101],"pre-trained":[103],"process":[104],"reward":[105],"(PRM)":[107],"serves":[108],"effective":[111],"alternative.":[112],"Consequently,":[113],"integrated":[115],"LECO":[116],"with":[117],"PRM":[118],"develop":[120],"new":[122],"LECO-R":[123],"model.":[124],"Experimental":[125],"results":[126],"demonstrate":[127],"effectiveness":[129],"of":[130],"our":[131],"overall":[132],"approach.":[133]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}