{"id":"https://openalex.org/W7125961870","doi":"https://doi.org/10.48550/arxiv.2601.19588","title":"From Atoms to Chains: Divergence-Guided Reasoning Curriculum for Unlabeled LLM Domain Adaptation","display_name":"From Atoms to Chains: Divergence-Guided Reasoning Curriculum for Unlabeled LLM Domain Adaptation","publication_year":2026,"publication_date":"2026-01-27","ids":{"openalex":"https://openalex.org/W7125961870","doi":"https://doi.org/10.48550/arxiv.2601.19588"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.19588","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.19588","pdf_url":"https://arxiv.org/pdf/2601.19588","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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/2601.19588","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122967595","display_name":"Yongqi Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Yongqi","raw_affiliation_strings":["Beijing Key Laboratory of Intelligent Information Technology , School of Computer Science and Technology , Beijing Institute of Technology","ByteDance China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Intelligent Information Technology , School of Computer Science and Technology , Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"ByteDance China","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124137030","display_name":"Xiaofeng Ji","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji, Xiaofeng","raw_affiliation_strings":["ByteDance China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance China","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159958424","display_name":"Jie Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Jie","raw_affiliation_strings":["ByteDance China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance China","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124065446","display_name":"Qingbin Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Qingbin","raw_affiliation_strings":["ByteDance China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance China","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101602532","display_name":"Xiong Xiao","orcid":"https://orcid.org/0000-0002-1793-5502","observed_orcids":["https://orcid.org/0000-0002-1793-5502"]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiong, Xiao","raw_affiliation_strings":["ByteDance China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance China","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120051058","display_name":"Zheming Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Zheming","raw_affiliation_strings":["ByteDance China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance China","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124070697","display_name":"Jian Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Jian","raw_affiliation_strings":["ByteDance China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance China","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125750231","display_name":"Minghui Qiu","orcid":"https://orcid.org/0000-0002-5184-9886","observed_orcids":["https://orcid.org/0000-0002-5184-9886"]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiu, Minghui","raw_affiliation_strings":["ByteDance China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance China","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011070646","display_name":"Xinxiao Wu","orcid":"https://orcid.org/0000-0002-2056-6947","observed_orcids":["https://orcid.org/0000-0002-2056-6947"]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Xinxiao","raw_affiliation_strings":["Beijing Key Laboratory of Intelligent Information Technology , School of Computer Science and Technology , Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Intelligent Information Technology , School of Computer Science and Technology , Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9502000212669373,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9502000212669373,"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":0.0430000014603138,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.00139999995008111,"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/unlabeled-data","display_name":"unlabeled data","score":0.6940000057220459},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.9570000171661377},{"id":"https://openalex.org/keywords/curriculum-learning","display_name":"curriculum learning","score":0.7129999995231628},{"id":"https://openalex.org/keywords/reasoning-chains","display_name":"reasoning chains","score":0.7059999704360962},{"id":"https://openalex.org/keywords/chain-of-thought-reasoning","display_name":"chain-of-thought reasoning","score":0.7329999804496765},{"id":"https://openalex.org/keywords/medical-domain","display_name":"medical domain","score":0.6019999980926514},{"id":"https://openalex.org/keywords/legal-domain","display_name":"legal domain","score":0.7910000085830688}],"concepts":[{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.6674000024795532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6256999969482422},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5752999782562256},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4629000127315521},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4339999854564667},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42500001192092896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4212000072002411},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.3986000120639801},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.3147999942302704},{"id":"https://openalex.org/C2992562121","wikidata":"https://www.wikidata.org/wiki/Q3817808","display_name":"Scientific reasoning","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.29820001125335693},{"id":"https://openalex.org/C185020186","wikidata":"https://www.wikidata.org/wiki/Q5370761","display_name":"Emergent curriculum","level":5,"score":0.28360000252723694},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.28299999237060547},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C33566652","wikidata":"https://www.wikidata.org/wiki/Q1065927","display_name":"Theme (computing)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.19588","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.19588","pdf_url":"https://arxiv.org/pdf/2601.19588","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2601.19588","doi":"https://doi.org/10.48550/arxiv.2601.19588","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.19588","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:2601.19588","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.19588","pdf_url":"https://arxiv.org/pdf/2601.19588","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8278999924659729,"display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7125961870.pdf","grobid_xml":"https://content.openalex.org/works/W7125961870.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7114780340","https://openalex.org/W7119542772","https://openalex.org/W7161010155","https://openalex.org/W4416036653","https://openalex.org/W7124437674","https://openalex.org/W7155197177","https://openalex.org/W7207595114","https://openalex.org/W4415036218","https://openalex.org/W4405426116","https://openalex.org/W7214097839"],"abstract_inverted_index":{"Adapting":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"to":[5,50,109,135,145,161,179,191,208],"specialized":[6],"domains":[7,222],"without":[8],"human-annotated":[9],"data":[10],"is":[11,59],"a":[12,45,52,71,103,124,137,171,199,240],"crucial":[13],"yet":[14],"formidable":[15],"challenge.":[16],"Widely":[17],"adopted":[18],"knowledge":[19,108,183,211],"distillation":[20],"methods":[21],"often":[22,84],"devolve":[23],"into":[24,212],"coarse-grained":[25],"mimicry,":[26],"where":[27],"the":[28,39,56,133,151,181,193,205,218,230,245,250],"student":[29,125,206,224,247],"model":[30,248],"inefficiently":[31],"targets":[32],"its":[33],"own":[34],"weaknesses":[35],"and":[36,126,156,185,220],"risks":[37],"inheriting":[38],"teacher's":[40,194],"reasoning":[41,110,121,143,196,214],"flaws.":[42],"This":[43],"exposes":[44],"critical":[46],"pedagogical":[47],"dilemma:":[48],"how":[49,207],"devise":[51],"reliable":[53],"curriculum":[54,178,202],"when":[55],"teacher":[57,127,134],"itself":[58],"not":[60],"an":[61,176],"infallible":[62],"expert.":[63],"Our":[64],"work":[65],"resolves":[66],"this":[67],"by":[68,112],"capitalizing":[69],"on":[70,88,93,223],"key":[72],"insight:":[73],"while":[74],"LLMs":[75],"may":[76],"exhibit":[77,85],"fallibility":[78],"in":[79,120,249],"complex,":[80],"holistic":[81],"reasoning,":[82],"they":[83],"high":[86],"fidelity":[87],"focused,":[89],"atomic":[90,107,147,164,177,210],"sub-problems.":[91],"Based":[92],"this,":[94],"we":[95],"propose":[96],"Divergence-Guided":[97],"Reasoning":[98],"Curriculum":[99],"(DGRC),":[100],"which":[101],"constructs":[102],"learning":[104],"path":[105],"from":[106,118],"chains":[111],"dynamically":[113],"deriving":[114],"two":[115],"complementary":[116],"curricula":[117],"disagreements":[119],"pathways.":[122],"When":[123],"produce":[128],"conflicting":[129],"results,":[130],"DGRC":[131,234],"directs":[132],"perform":[136],"diagnostic":[138],"analysis:":[139],"it":[140],"analyzes":[141],"both":[142],"paths":[144],"formulate":[146],"queries":[148,160],"that":[149,203],"target":[150],"specific":[152],"points":[153],"of":[154,226,232],"divergence,":[155],"then":[157,169],"self-answers":[158],"these":[159],"create":[162],"high-confidence":[163],"question-answer":[165],"pairs.":[166],"These":[167],"pairs":[168],"serve":[170],"dual":[172],"purpose:":[173],"(1)":[174],"providing":[175],"rectify":[180],"student's":[182],"gaps,":[184],"(2)":[186],"serving":[187],"as":[188],"factual":[189],"criteria":[190],"filter":[192],"original":[195],"chains,":[197],"yielding":[198],"verified":[200],"CoT":[201],"teaches":[204],"integrate":[209],"complete":[213],"paths.":[215],"Experiments":[216],"across":[217],"medical":[219,251],"legal":[221],"models":[225],"various":[227],"sizes":[228],"demonstrate":[229],"effectiveness":[231],"our":[233,237],"framework.":[235],"Notably,":[236],"method":[238],"achieves":[239],"7.76%":[241],"relative":[242],"improvement":[243],"for":[244],"1.5B":[246],"domain":[252],"over":[253],"strong":[254],"unlabeled":[255],"baseline.":[256]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-01-29T00:00:00"}