{"id":"https://openalex.org/W4408347311","doi":"https://doi.org/10.1109/icassp49660.2025.10887840","title":"Self-Enhanced Reasoning Training: Activating Latent Reasoning in Small Models for Enhanced Reasoning Distillation","display_name":"Self-Enhanced Reasoning Training: Activating Latent Reasoning in Small Models for Enhanced Reasoning Distillation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408347311","doi":"https://doi.org/10.1109/icassp49660.2025.10887840"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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":"https://openalex.org/A5100619206","display_name":"Yong Zhang","orcid":"https://orcid.org/0000-0003-1436-5951"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Zhang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101459239","display_name":"Bingyuan Zhang","orcid":"https://orcid.org/0009-0003-6000-6631"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingyuan Zhang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101511899","display_name":"Zhitao Li","orcid":"https://orcid.org/0000-0001-9967-1303"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhitao Li","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351375","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-0722-028X"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065576761","display_name":"Ning Cheng","orcid":"https://orcid.org/0000-0003-0909-5328"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Cheng","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059638789","display_name":"Minchuan Chen","orcid":"https://orcid.org/0009-0001-1512-6672"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minchuan Chen","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101714910","display_name":"Wei Tao","orcid":"https://orcid.org/0009-0004-2928-3451"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Wei","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101542950","display_name":"Jun Ma","orcid":"https://orcid.org/0000-0001-5633-6839"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Ma","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702012","display_name":"Shaojun Wang","orcid":"https://orcid.org/0000-0002-3680-9464"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaojun Wang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045433698","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0002-3298-3705"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4401726822"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.8899999856948853,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.8899999856948853,"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/T10028","display_name":"Topic Modeling","score":0.829800009727478,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.8012999892234802,"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":0.6672609448432922},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.5257854461669922},{"id":"https://openalex.org/keywords/deductive-reasoning","display_name":"Deductive reasoning","score":0.5238861441612244},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.5143440961837769},{"id":"https://openalex.org/keywords/qualitative-reasoning","display_name":"Qualitative reasoning","score":0.4670359790325165},{"id":"https://openalex.org/keywords/opportunistic-reasoning","display_name":"Opportunistic reasoning","score":0.4657949209213257},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.46440884470939636},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.46297428011894226},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.46005862951278687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44026806950569153},{"id":"https://openalex.org/keywords/analytic-reasoning","display_name":"Analytic reasoning","score":0.423876017332077},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32560497522354126},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.13741040229797363},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.10034173727035522}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6672609448432922},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.5257854461669922},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.5238861441612244},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.5143440961837769},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.4670359790325165},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.4657949209213257},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.46440884470939636},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.46297428011894226},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.46005862951278687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44026806950569153},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.423876017332077},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32560497522354126},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.13741040229797363},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.10034173727035522},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2963736842","https://openalex.org/W3159959439","https://openalex.org/W4385570191","https://openalex.org/W4385571011","https://openalex.org/W4385571219","https://openalex.org/W4385571260","https://openalex.org/W4385572016","https://openalex.org/W4389520139","https://openalex.org/W4389523706","https://openalex.org/W4389524052","https://openalex.org/W4393160586","https://openalex.org/W6638523607","https://openalex.org/W6755829550","https://openalex.org/W6778883912","https://openalex.org/W6800875267","https://openalex.org/W6809646742","https://openalex.org/W6810738896","https://openalex.org/W6811284106","https://openalex.org/W6838865847","https://openalex.org/W6850625674","https://openalex.org/W6861521026"],"related_works":["https://openalex.org/W2347305376","https://openalex.org/W1816891706","https://openalex.org/W3081308103","https://openalex.org/W94330105","https://openalex.org/W2392104753","https://openalex.org/W1540734423","https://openalex.org/W2188850991","https://openalex.org/W2349790191","https://openalex.org/W1523730659","https://openalex.org/W2574333357"],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3,138],"large":[4],"language":[5],"models":[6,28,40,60,105,126,130],"(LLMs)":[7],"has":[8],"significantly":[9],"enhanced":[10],"their":[11,80,142],"reasoning":[12,35,42,53,64,101,111,136,145],"abilities,":[13],"enabling":[14],"increasingly":[15],"complex":[16],"tasks.":[17],"However,":[18],"these":[19,73],"capabilities":[20,102],"often":[21,76],"diminish":[22],"in":[23,103,144],"smaller,":[24],"more":[25],"computationally":[26],"efficient":[27],"like":[29],"GPT-2.":[30],"Recent":[31],"research":[32],"shows":[33],"that":[34,58,132],"distillation":[36],"can":[37,61],"help":[38],"small":[39,59,104,139],"acquire":[41],"capabilities,":[43],"but":[44],"most":[45],"existing":[46],"methods":[47],"focus":[48],"primarily":[49],"on":[50,108],"improving":[51,141],"teacher-generated":[52],"paths.":[54],"Our":[55],"observations":[56],"reveal":[57],"generate":[62],"high-quality":[63],"paths":[65,74,112],"during":[66],"sampling,":[67],"even":[68],"without":[69],"chain-of-thought":[70],"prompting,":[71],"though":[72],"are":[75],"latent":[77,100],"due":[78],"to":[79],"low":[81],"probability":[82],"under":[83,113],"standard":[84],"decoding":[85],"strategies.":[86],"To":[87],"address":[88],"this,":[89],"we":[90],"propose":[91],"Self-Enhanced":[92],"Reasoning":[93],"Training":[94],"(SERT),":[95],"which":[96],"activates":[97],"and":[98,124],"leverages":[99],"through":[106],"self-training":[107],"filtered,":[109],"self-generated":[110],"zero-shot":[114],"conditions.":[115],"Experiments":[116],"using":[117],"OpenAI\u2019s":[118],"GPT-3.5":[119],"as":[120,127],"the":[121,128,135],"teacher":[122],"model":[123],"GPT-2":[125],"student":[129],"demonstrate":[131],"SERT":[133],"enhances":[134],"abilities":[137],"models,":[140],"performance":[143],"distillation.":[146]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}