{"id":"https://openalex.org/W7150869880","doi":"https://doi.org/10.48550/arxiv.2604.02819","title":"Student-in-the-Loop Chain-of-Thought Distillation via Generation-Time Selection","display_name":"Student-in-the-Loop Chain-of-Thought Distillation via Generation-Time Selection","publication_year":2026,"publication_date":"2026-04-03","ids":{"openalex":"https://openalex.org/W7150869880","doi":"https://doi.org/10.48550/arxiv.2604.02819"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2604.02819","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2604.02819","pdf_url":"https://arxiv.org/pdf/2604.02819","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2604.02819","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019601671","display_name":"Chaoqun He","orcid":"https://orcid.org/0009-0001-5058-541X","observed_orcids":["https://orcid.org/0009-0001-5058-541X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Chaoqun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125901983","display_name":"Yingfa Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yingfa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014699953","display_name":"Chaojun Xiao","orcid":"https://orcid.org/0000-0001-6039-0942","observed_orcids":["https://orcid.org/0000-0001-6039-0942","https://orcid.org/0009-0003-4475-0946"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Chaojun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133029791","display_name":"Xu Han","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137048088","display_name":"Lijie Wen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen, Lijie","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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5098000168800354,"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/T10028","display_name":"Topic Modeling","score":0.5098000168800354,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.20900000631809235,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.06880000233650208,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/chain-of-thought-distillation","display_name":"chain-of-thought distillation","score":0.9190000295639038},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.8999999761581421},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.5529999732971191},{"id":"https://openalex.org/keywords/mathematical-reasoning","display_name":"mathematical reasoning","score":0.871999979019165},{"id":"https://openalex.org/keywords/teacher-student-learning","display_name":"teacher-student learning","score":0.5630000233650208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7116000056266785},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6545000076293945},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6474999785423279},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5996000170707703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5968999862670898},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5461000204086304},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4961000084877014},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.4404999911785126},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4388999938964844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4334000051021576},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.40540000796318054},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.33629998564720154},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3068000078201294},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.2906000018119812},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2605000138282776}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2604.02819","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2604.02819","pdf_url":"https://arxiv.org/pdf/2604.02819","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2604.02819","doi":"https://doi.org/10.48550/arxiv.2604.02819","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.02819","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2604.02819","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2604.02819","pdf_url":"https://arxiv.org/pdf/2604.02819","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.9235000014305115}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7204933937","https://openalex.org/W7138152349","https://openalex.org/W7166802716","https://openalex.org/W7124262579","https://openalex.org/W7081154480","https://openalex.org/W4416034022","https://openalex.org/W7114780340","https://openalex.org/W4416036844","https://openalex.org/W7166843076","https://openalex.org/W7160451680"],"abstract_inverted_index":{"Large":[0],"reasoning":[1,18,33,69,117,129,169],"models":[2,22],"achieve":[3],"strong":[4],"performance":[5],"on":[6,44,53,127],"complex":[7],"tasks":[8],"through":[9],"long":[10],"chain-of-thought":[11],"(CoT)":[12],"trajectories,":[13,100,170],"but":[14],"directly":[15],"transferring":[16],"such":[17,57],"processes":[19],"to":[20,153],"smaller":[21],"remains":[23],"challenging.":[24],"A":[25],"key":[26],"difficulty":[27],"is":[28],"that":[29,71,91,132,162],"not":[30],"all":[31],"teacher-generated":[32],"trajectories":[34,48],"are":[35],"suitable":[36],"for":[37,179],"student":[38,102],"learning.":[39],"Existing":[40],"approaches":[41],"typically":[42],"rely":[43],"post-hoc":[45],"filtering,":[46],"selecting":[47],"after":[49],"full":[50],"generation":[51,62,178],"based":[52],"heuristic":[54],"criteria.":[55],"However,":[56],"methods":[58],"cannot":[59],"control":[60],"the":[61,74,101,107,112,172],"process":[63],"itself":[64],"and":[65,119,139,151,167],"may":[66],"still":[67],"produce":[68],"paths":[70,118],"lie":[72],"outside":[73],"student's":[75],"learning":[76],"capacity.":[77],"To":[78],"address":[79],"this":[80],"limitation,":[81],"we":[82],"propose":[83],"Gen-SSD":[84,133,163],"(Generation-time":[85],"Self-Selection":[86],"Distillation),":[87],"a":[88],"student-in-the-loop":[89],"framework":[90],"performs":[92],"generation-time":[93],"selection.":[94],"Instead":[95],"of":[96,114,123,144,174],"passively":[97],"consuming":[98],"complete":[99],"evaluates":[103],"candidate":[104],"continuations":[105],"during":[106,177],"teacher's":[108],"sampling":[109],"process,":[110],"guiding":[111],"expansion":[113],"only":[115],"learnable":[116,168],"enabling":[120],"early":[121],"pruning":[122],"unhelpful":[124],"branches.":[125],"Experiments":[126],"mathematical":[128],"benchmarks":[130],"demonstrate":[131],"consistently":[134],"outperforms":[135],"standard":[136],"knowledge":[137],"distillation":[138],"recent":[140],"baselines,":[141],"with":[142],"improvements":[143],"around":[145],"5.9":[146],"points":[147,155],"over":[148,156],"Standard":[149],"KD":[150],"up":[152],"4.7":[154],"other":[157],"baselines.":[158],"Further":[159],"analysis":[160],"shows":[161],"produces":[164],"more":[165],"stable":[166],"highlighting":[171],"importance":[173],"incorporating":[175],"supervision":[176],"effective":[180],"distillation.":[181]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-04-07T00:00:00"}