{"id":"https://openalex.org/W4412888459","doi":"https://doi.org/10.18653/v1/2025.findings-acl.513","title":"SIKeD: Self-guided Iterative Knowledge Distillation for Mathematical Reasoning","display_name":"SIKeD: Self-guided Iterative Knowledge Distillation for Mathematical Reasoning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888459","doi":"https://doi.org/10.18653/v1/2025.findings-acl.513"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.513","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.513","pdf_url":"https://aclanthology.org/2025.findings-acl.513.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.513.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shivam Adarsh","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Shivam Adarsh","raw_affiliation_strings":["University of Copenhagen ETH Zurich ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Copenhagen ETH Zurich ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031480753","display_name":"Kumar Shridhar","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Kumar Shridhar","raw_affiliation_strings":["University of Copenhagen ETH Zurich ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Copenhagen ETH Zurich ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041145688","display_name":"\u00c7a\u011flar G\u00fcl\u00e7ehre","orcid":"https://orcid.org/0009-0003-4124-1687"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caglar Gulcehre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029504586","display_name":"Nicholas Monath","orcid":"https://orcid.org/0000-0002-5135-2423"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicholas Monath","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002316432","display_name":"Mrinmaya Sachan","orcid":"https://orcid.org/0000-0001-8787-8681"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mrinmaya Sachan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9868","last_page":"9880"},"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":0.9581000208854675,"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":0.9581000208854675,"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":0.6762502193450928},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5942298173904419},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4817109704017639},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18769776821136475},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.10235381126403809},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.08904704451560974}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6762502193450928},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5942298173904419},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4817109704017639},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18769776821136475},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.10235381126403809},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.08904704451560974}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.513","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.513","pdf_url":"https://aclanthology.org/2025.findings-acl.513.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"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/e4d49d85-a725-44bf-8508-2383225f4271","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/e4d49d85-a725-44bf-8508-2383225f4271","pdf_url":"https://curis.ku.dk/ws/files/535491521/SIKeD.pdf","source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"contributionToPeriodical"},{"id":"pmh:doi:10.3929/ethz-c-000794711","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/794711","pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.513","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.513","pdf_url":"https://aclanthology.org/2025.findings-acl.513.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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888459.pdf","grobid_xml":"https://content.openalex.org/works/W4412888459.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],"(LLMs)":[3],"can":[4,28],"transfer":[5],"their":[6,85],"reasoning":[7,19,25,31,78,192],"skills":[8],"to":[9,15,22,45,57,76,107,123,151,168,181],"smaller":[10,39,72,105,116,166,203],"models":[11,40,73,204],"by":[12],"teaching":[13],"them":[14],"generate":[16],"the":[17,47,62,101,104,115,125,130,153,157,165],"intermediate":[18],"process":[20],"required":[21],"solve":[23,30,77,182],"multistep":[24],"tasks.While":[26],"LLMs":[27,48],"accurately":[29],"tasks":[32,79],"through":[33],"various":[34,190],"strategies,":[35],"even":[36],"without":[37],"fine-tuning,":[38],"are":[41],"not":[42],"expressive":[43],"enough":[44],"fit":[46],"distribution":[49],"on":[50,65,149,189],"all":[51],"strategies":[52,113],"when":[53,74],"distilled":[54],"and":[55,114],"tend":[56],"prioritize":[58],"one":[59,66],"strategy":[60,67,128,171],"over":[61],"others.This":[63],"reliance":[64],"poses":[68],"a":[69,92,109,136,145,175,183],"challenge":[70],"for":[71,129,141,174],"attempting":[75],"that":[80,195],"may":[81],"be":[82],"difficult":[83],"with":[84,156],"preferred":[86],"strategy.To":[87],"address":[88],"this,":[89],"we":[90],"propose":[91],"distillation":[93,161,200],"method":[94],"SIKeD:":[95],"Self-guided":[96],"Iterative":[97],"Knowledge":[98],"Distillation,":[99],"where":[100,140],"LLM":[102,154],"teaches":[103],"model":[106,117,167],"approach":[108],"task":[110,177,184],"using":[111,185],"different":[112,186,206],"uses":[118],"its":[119],"self-generated":[120,158],"on-policy":[121],"outputs":[122],"choose":[124],"most":[126],"suitable":[127,173],"given":[131,176],"task.The":[132],"training":[133,143],"continues":[134],"in":[135],"self-guided":[137],"iterative":[138],"manner,":[139],"each":[142],"iteration,":[144],"decision":[146],"is":[147,172],"made":[148],"how":[150],"combine":[152],"data":[155],"outputs.Unlike":[159],"traditional":[160,199],"methods,":[162],"SIKeD":[163,196],"allows":[164],"learn":[169],"which":[170],"while":[178],"continuously":[179],"learning":[180],"strategies.Our":[187],"experiments":[188],"mathematical":[191],"datasets":[193],"show":[194],"significantly":[197],"outperforms":[198],"techniques":[201],"across":[202],"of":[205],"sizes":[207],"1":[208],".":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}