{"id":"https://openalex.org/W4412944484","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1301","title":"Small Models Struggle to Learn from Strong Reasoners","display_name":"Small Models Struggle to Learn from Strong Reasoners","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944484","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1301"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1301","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1301","pdf_url":"https://aclanthology.org/2025.findings-acl.1301.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.1301.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039253379","display_name":"Yuetai Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuetai Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044182336","display_name":"Yue Xiang","orcid":"https://orcid.org/0000-0001-6580-9378"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Yue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028990387","display_name":"Zhangchen Xu","orcid":"https://orcid.org/0000-0002-6971-412X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhangchen Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007846132","display_name":"Fengqing Jiang","orcid":"https://orcid.org/0009-0002-9077-2399"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fengqing Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018806127","display_name":"Luyao Niu","orcid":"https://orcid.org/0000-0001-8591-5522"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luyao Niu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114909628","display_name":"Bill Yuchen Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bill Yuchen Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052064870","display_name":"Bhaskar Ramasubramanian","orcid":"https://orcid.org/0000-0002-2166-7838"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhaskar Ramasubramanian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079723268","display_name":"Radha Poovendran","orcid":"https://orcid.org/0000-0003-0269-8097"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Radha Poovendran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0843,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.91932059,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"25366","last_page":"25394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11810","display_name":"Complex Systems and Decision Making","score":0.08810000121593475,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11810","display_name":"Complex Systems and Decision Making","score":0.08810000121593475,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4958527982234955}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4958527982234955}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1301","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1301","pdf_url":"https://aclanthology.org/2025.findings-acl.1301.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1301","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1301","pdf_url":"https://aclanthology.org/2025.findings-acl.1301.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G5809100787","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G6098521345","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6360409883","display_name":null,"funder_award_id":"2229876","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6906012493","display_name":null,"funder_award_id":"FA9550-23-1-0208","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306110","display_name":"U.S. Department of Homeland Security","ror":"https://ror.org/00jyr0d86"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944484.pdf","grobid_xml":"https://content.openalex.org/works/W4412944484.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,16,34],"(LLMs)":[3],"excel":[4],"in":[5],"complex":[6],"reasoning":[7,12,45,59,82,92,108,132,136],"tasks,":[8],"and":[9,87,96,126],"distilling":[10],"their":[11,65],"capabilities":[13],"into":[14],"smaller":[15,97],"has":[17],"shown":[18],"promise.However,":[19],"we":[20,26,71],"uncover":[21],"an":[22],"interesting":[23],"phenomenon,":[24],"which":[25],"term":[27],"the":[28,119,128],"Small":[29],"Model":[30],"Learnability":[31],"Gap:":[32],"small":[33,106],"(3B":[35],"parameters)":[36],"do":[37],"not":[38],"consistently":[39],"benefit":[40],"from":[41,48,93],"long":[42,86],"chain-of-thought":[43],"(CoT)":[44],"or":[46,91],"distillation":[47,125],"larger":[49,95],"models.Instead,":[50],"they":[51],"perform":[52],"better":[53,62],"when":[54],"fine-tuned":[55],"on":[56,113],"shorter,":[57],"simpler":[58],"chains":[60],"that":[61,80,101],"align":[63],"with":[64],"intrinsic":[66],"learning":[67],"capacity.To":[68],"address":[69],"this,":[70],"propose":[72],"Mix":[73,102],"Distillation,":[74],"a":[75],"simple":[76],"yet":[77],"effective":[78,135],"strategy":[79],"balances":[81],"complexity":[83,133],"by":[84],"combining":[85],"short":[88],"CoT":[89],"examples":[90],"both":[94],"models.Our":[98],"experiments":[99],"demonstrate":[100],"Distillation":[103],"significantly":[104],"improves":[105],"model":[107,124],"performance":[109],"compared":[110],"to":[111],"training":[112],"either":[114],"data":[115],"alone.These":[116],"findings":[117],"highlight":[118],"limitations":[120],"of":[121,130],"direct":[122],"strong":[123],"underscore":[127],"importance":[129],"adapting":[131],"for":[134],"capability":[137],"transfer.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}