{"id":"https://openalex.org/W4416036969","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.377","title":"Enhancing Reasoning Abilities of Small LLMs with Cognitive Alignment","display_name":"Enhancing Reasoning Abilities of Small LLMs with Cognitive Alignment","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036969","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.377"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.377","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.377","pdf_url":"https://aclanthology.org/2025.emnlp-main.377.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.377.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103031810","display_name":"Waijiao Cai","orcid":"https://orcid.org/0000-0003-4730-1145"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wenrui Cai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373451","display_name":"Chengyu Wang","orcid":"https://orcid.org/0000-0003-1010-9678"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengyu Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022633033","display_name":"Junbing Yan","orcid":"https://orcid.org/0009-0001-5588-4793"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junbing Yan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049316142","display_name":"Jun Huang","orcid":"https://orcid.org/0000-0002-2022-5747"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Huang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5065484189","display_name":"Xiangzhong Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangzhong Fang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103031810"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18438066,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7434","last_page":"7449"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.5205000042915344,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.5205000042915344,"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/T10636","display_name":"Innovative Teaching and Learning Methods","score":0.06669999659061432,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.05719999969005585,"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/cognition","display_name":"Cognition","score":0.6216999888420105},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.30169999599456787},{"id":"https://openalex.org/keywords/social-cognitive-theory","display_name":"Social cognitive theory","score":0.30140000581741333}],"concepts":[{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.6216999888420105},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.510200023651123},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.47350001335144043},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3555999994277954},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.31779998540878296},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C14564219","wikidata":"https://www.wikidata.org/wiki/Q383646","display_name":"Social cognitive theory","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2842000126838684},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.27469998598098755},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.26080000400543213}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.377","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.377","pdf_url":"https://aclanthology.org/2025.emnlp-main.377.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.377","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.377","pdf_url":"https://aclanthology.org/2025.emnlp-main.377.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036969.pdf","grobid_xml":"https://content.openalex.org/works/W4416036969.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"reasoning":[1,5,35,45,157,165,174],"capabilities":[2,117],"of":[3,76,99,118,136,159,179],"large":[4,61,189],"models":[6,42,161],"(LRMs),":[7],"such":[8],"as":[9],"OpenAI's":[10],"o1":[11],"and":[12,47,70,123,131],"DeepSeek-R1,":[13],"have":[14],"seen":[15],"substantial":[16,74],"advancements":[17],"through":[18],"deep":[19],"thinking.However,":[20],"these":[21,125],"enhancements":[22],"come":[23],"with":[24,51,167],"significant":[25],"resource":[26],"demands,":[27],"underscoring":[28],"the":[29,110,115,129,134,137,141,147,156,177],"need":[30],"for":[31,90],"training":[32,91],"effective":[33],"small":[34,41],"models.A":[36],"critical":[37],"challenge":[38],"is":[39],"that":[40],"possess":[43],"different":[44],"capacities":[46],"cognitive":[48,116,169],"trajectories":[49],"compared":[50],"their":[52,164,168],"larger":[53],"counterparts.Hence,":[54],"directly":[55],"distilling":[56],"chain-of-thought":[57],"(CoT)":[58],"rationales":[59,112],"from":[60],"LRMs":[62],"to":[63,114,153],"smaller":[64,92,119,160],"ones":[65],"can":[66],"sometimes":[67],"be":[68],"ineffective":[69],"often":[71],"requires":[72],"a":[73,84,188],"amount":[75],"annotated":[77],"data.In":[78],"this":[79],"paper,":[80],"we":[81,144],"first":[82],"introduce":[83],"novel":[85],"Critique-Rethink-Verify":[86],"(CRV)":[87],"system,":[88,143],"designed":[89],"yet":[93],"powerful":[94],"LRMs.Our":[95],"CRV":[96,142],"system":[97],"consists":[98],"multiple":[100],"LLM":[101],"agents,":[102],"each":[103],"specializing":[104],"in":[105],"unique":[106],"tasks:":[107],"(i)":[108],"critiquing":[109],"CoT":[111],"according":[113],"models,":[120],"(ii)":[121],"rethinking":[122],"refining":[124],"CoTs":[126],"based":[127],"on":[128,140,172],"critiques,":[130],"(iii)":[132],"verifying":[133],"correctness":[135],"refined":[138],"results.Building":[139],"further":[145],"propose":[146],"Cognitive":[148],"Preference":[149],"Optimization":[150],"(CogPO)":[151],"algorithm":[152],"continuously":[154],"enhance":[155],"abilities":[158],"by":[162,187],"aligning":[163],"processes":[166],"capacities.Comprehensive":[170],"evaluations":[171],"challenging":[173],"benchmarks":[175],"demonstrate":[176],"efficacy":[178],"our":[180],"CRV+CogPO":[181],"framework,":[182],"which":[183],"outperforms":[184],"other":[185],"methods":[186],"margin.":[190],"1":[191]},"counts_by_year":[],"updated_date":"2026-03-14T06:41:57.775601","created_date":"2025-11-08T00:00:00"}