{"id":"https://openalex.org/W4416035340","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1675","title":"Convergence and Divergence of Language Models under Different Random Seeds","display_name":"Convergence and Divergence of Language Models under Different Random Seeds","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035340","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1675"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1675","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1675","pdf_url":"https://aclanthology.org/2025.emnlp-main.1675.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1675.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120308815","display_name":"Finlay Fehlauer","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Finlay Fehlauer","raw_affiliation_strings":["ETH Zrich University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"ETH Zrich University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039468724","display_name":"Kyle Mahowald","orcid":"https://orcid.org/0000-0002-9786-8716"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle Mahowald","raw_affiliation_strings":["ETH Zrich University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"ETH Zrich University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102825308","display_name":"Tiago Pimentel","orcid":"https://orcid.org/0000-0002-5159-4641"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tiago Pimentel","raw_affiliation_strings":["ETH Zrich University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"ETH Zrich University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5120308815"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37482961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"32970","last_page":"32979"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.10779999941587448,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.10779999941587448,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.0868000015616417,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.08429999649524689,"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/convergence","display_name":"Convergence (economics)","score":0.6043999791145325},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.5684000253677368},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.3319999873638153},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3206000030040741},{"id":"https://openalex.org/keywords/point-process","display_name":"Point process","score":0.3043000102043152},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.2937999963760376},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.290800005197525}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6043999791145325},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5684000253677368},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.539900004863739},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4169999957084656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3644999861717224},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C88871306","wikidata":"https://www.wikidata.org/wiki/Q7208287","display_name":"Point process","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30309998989105225},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C127491075","wikidata":"https://www.wikidata.org/wiki/Q7617825","display_name":"Stochastic modelling","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2630999982357025},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25690001249313354},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.25220000743865967},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1675","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1675","pdf_url":"https://aclanthology.org/2025.emnlp-main.1675.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1675","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1675","pdf_url":"https://aclanthology.org/2025.emnlp-main.1675.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G841210225","display_name":"CAREER: Investigating linguistic and cognitive abstractions for solving word problems in minds and machines","funder_award_id":"2339729","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035340.pdf","grobid_xml":"https://content.openalex.org/works/W4416035340.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,39,63],"investigate":[4],"the":[5,19,138,141],"convergence":[6,17,29,43,108],"of":[7,33,140],"language":[8],"models":[9,67,76],"(LMs)":[10],"trained":[11],"under":[12],"different":[13],"random":[14],"seeds,":[15],"measuring":[16],"as":[18,30],"expected":[20],"per-token":[21],"Kullback-Leibler":[22],"(KL)":[23],"divergence":[24],"across":[25,111],"seeds.By":[26],"comparing":[27],"LM":[28],"a":[31,41,51,55,60,84],"function":[32,117],"model":[34,86,145],"size":[35,87],"and":[36,58,116,121,129],"training":[37,72],"checkpoint,":[38],"identify":[40],"four-phase":[42],"pattern:":[44],"(i)":[45],"an":[46],"initial":[47],"uniform":[48],"phase,":[49,53,57],"(ii)":[50],"sharp-convergence":[52],"(iii)":[54],"sharp-divergence":[56],"(iv)":[59],"slowreconvergence":[61],"phase.Further,":[62],"observe":[64],"that":[65,83,107,136],"larger":[66],"reconverge":[68],"faster":[69,120],"in":[70,144],"later":[71],"stages,":[73],"while":[74],"smaller":[75],"never":[77],"actually":[78],"reconverge;":[79],"these":[80],"results":[81],"suggest":[82],"certain":[85],"may":[88],"be":[89],"necessary":[90],"to":[91,97],"learn":[92],"stable":[93],"distributions.Restricting":[94],"our":[95,132],"analysis":[96],"specific":[98],"token":[99],"frequencies":[100],"or":[101],"part-of-speech":[102],"(PoS)":[103],"tags":[104],"further":[105],"reveals":[106],"is":[109],"uneven":[110],"linguistic":[112],"categories:":[113],"frequent":[114],"tokens":[115,128],"words":[118],"converge":[119],"more":[122],"reliably":[123],"than":[124],"their":[125],"counterparts":[126],"(infrequent":[127],"content":[130],"words).Overall,":[131],"findings":[133],"highlight":[134],"factors":[135],"influence":[137],"stability":[139],"learned":[142],"distributions":[143],"training.":[146]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-11-08T00:00:00"}