{"id":"https://openalex.org/W4412888651","doi":"https://doi.org/10.18653/v1/2025.findings-acl.291","title":"Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst","display_name":"Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888651","doi":"https://doi.org/10.18653/v1/2025.findings-acl.291"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.291","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.291","pdf_url":"https://aclanthology.org/2025.findings-acl.291.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.291.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101913265","display_name":"Hongru Wang","orcid":"https://orcid.org/0009-0008-2450-0081"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongru Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037942269","display_name":"Deng Cai","orcid":"https://orcid.org/0000-0001-9817-4065"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng Cai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019101763","display_name":"Wanjun Zhong","orcid":"https://orcid.org/0009-0007-2236-228X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wanjun Zhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067715252","display_name":"Shijue Huang","orcid":"https://orcid.org/0000-0001-9443-7948"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shijue Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066422711","display_name":"Jeff Z. Pan","orcid":"https://orcid.org/0000-0002-9779-2088"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeff Z. Pan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103008895","display_name":"Zeming Liu","orcid":"https://orcid.org/0000-0002-3691-8097"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeming Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5008208316","display_name":"Kam\u2010Fai Wong","orcid":"https://orcid.org/0000-0002-9427-5659"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kam-Fai Wong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5578","last_page":"5596"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.949999988079071,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.949999988079071,"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":0.9484000205993652,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9390000104904175,"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":0.6350613236427307},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.531862199306488},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.528872013092041},{"id":"https://openalex.org/keywords/verbal-reasoning","display_name":"Verbal reasoning","score":0.5114020705223083},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.5091087222099304},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.479912132024765},{"id":"https://openalex.org/keywords/opportunistic-reasoning","display_name":"Opportunistic reasoning","score":0.4613492786884308},{"id":"https://openalex.org/keywords/analytic-reasoning","display_name":"Analytic reasoning","score":0.4450313150882721},{"id":"https://openalex.org/keywords/deductive-reasoning","display_name":"Deductive reasoning","score":0.42571061849594116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38359734416007996},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37661978602409363},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.14670014381408691},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1412646472454071},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.13443133234977722}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6350613236427307},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.531862199306488},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.528872013092041},{"id":"https://openalex.org/C36964233","wikidata":"https://www.wikidata.org/wiki/Q7920942","display_name":"Verbal reasoning","level":3,"score":0.5114020705223083},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.5091087222099304},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.479912132024765},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.4613492786884308},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.4450313150882721},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.42571061849594116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38359734416007996},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37661978602409363},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.14670014381408691},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1412646472454071},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.13443133234977722},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.291","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.291","pdf_url":"https://aclanthology.org/2025.findings-acl.291.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.291","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.291","pdf_url":"https://aclanthology.org/2025.findings-acl.291.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":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G3291373823","display_name":null,"funder_award_id":"KPF23GWP20","funder_id":"https://openalex.org/F4320322942","funder_display_name":"Chinese University of Hong Kong"},{"id":"https://openalex.org/G8125344204","display_name":null,"funder_award_id":"4055209","funder_id":"https://openalex.org/F4320322942","funder_display_name":"Chinese University of Hong Kong"}],"funders":[{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888651.pdf","grobid_xml":"https://content.openalex.org/works/W4412888651.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4232020376","https://openalex.org/W3081308103","https://openalex.org/W2347305376","https://openalex.org/W3171780880","https://openalex.org/W1974525301","https://openalex.org/W94330105","https://openalex.org/W4404313183","https://openalex.org/W2077137711","https://openalex.org/W2319216046","https://openalex.org/W4385571345"],"abstract_inverted_index":{"Inference-time":[0],"scaling":[1],"has":[2],"attracted":[3],"much":[4],"attention":[5],"which":[6,89],"significantly":[7],"enhance":[8],"the":[9,22,57,102,165,175],"performance":[10,68,105],"of":[11,24,124,150],"Large":[12],"Language":[13,53],"Models":[14],"(LLMs)":[15],"in":[16,34,114,172],"complex":[17],"reasoning":[18,28,84,93,131,170],"tasks":[19],"by":[20],"increasing":[21],"length":[23],"Chain-of-Thought.These":[25],"longer":[26,62],"intermediate":[27],"rationales":[29],"embody":[30],"various":[31],"meta-reasoning":[32],"skills":[33],"human":[35],"cognition,":[36],"such":[37,154],"as":[38,91,155],"reflection":[39],"and":[40,46,65,111,137,168],"decomposition,":[41],"being":[42],"difficult":[43],"to":[44,81],"create":[45],"acquire.In":[47],"this":[48],"work,":[49],"we":[50,95],"introduce":[51],"Self-Reasoning":[52],"Model":[54],"(SRLM),":[55],"where":[56],"model":[58],"itself":[59],"can":[60],"synthesize":[61],"CoT":[63],"data":[64],"iteratively":[66],"improve":[67],"through":[69],"self-training.By":[70],"incorporating":[71],"a":[72,92],"few":[73],"demonstration":[74],"examples":[75],"(i.e.,":[76],"1,000":[77],"samples)":[78],"on":[79,139],"how":[80],"unfold":[82],"hidden":[83],"chains":[85],"from":[86],"existing":[87],"responses,":[88],"act":[90],"catalyst,":[94],"demonstrate":[96],"that":[97],"SRLM":[98,118,173],"not":[99],"only":[100],"enhances":[101],"model's":[103],"initial":[104],"but":[106],"also":[107],"ensures":[108],"more":[109,125,145,148],"stable":[110],"consistent":[112],"improvements":[113,146],"subsequent":[115],"iterations.Our":[116],"proposed":[117],"achieves":[119],"an":[120],"average":[121,158],"absolute":[122,156],"improvement":[123,159],"than":[126],"+2.5":[127],"points":[128],"across":[129],"five":[130],"tasks:":[132],"MMLU,":[133],"GSM8K,":[134],"ARC-C,":[135],"Hel-laSwag,":[136],"BBH":[138],"two":[140],"backbone":[141],"models.Moreover,":[142],"it":[143],"brings":[144],"with":[147,160],"times":[149],"sampling":[151,162],"during":[152],"inference,":[153],"+7.89":[157],"64":[161],"times,":[163],"revealing":[164],"in-depth,":[166],"diverse":[167],"creative":[169],"paths":[171],"against":[174],"strong":[176],"baseline.":[177]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}