{"id":"https://openalex.org/W4416058043","doi":"https://doi.org/10.1145/3799830.3799852","title":"Adapting Multilingual Models to Code-Mixed Tasks via Model Merging","display_name":"Adapting Multilingual Models to Code-Mixed Tasks via Model Merging","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W4416058043","doi":"https://doi.org/10.1145/3799830.3799852"},"language":null,"primary_location":{"id":"doi:10.1145/3799830.3799852","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799830.3799852","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM IKDD International Conference on Data Science","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3799830.3799852","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083888032","display_name":"Prashant Kodali","orcid":"https://orcid.org/0000-0002-7542-6802"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Prashant Kodali","raw_affiliation_strings":["IIIT Hyderabad, Hyderabad, Telangana, India"],"raw_orcid":"https://orcid.org/0000-0002-7542-6802","affiliations":[{"raw_affiliation_string":"IIIT Hyderabad, Hyderabad, Telangana, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119756277","display_name":"Vaishnavi Shivkumar","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vaishnavi Shivkumar","raw_affiliation_strings":["IIIT Hyderabad, Hyderabad, India"],"raw_orcid":"https://orcid.org/0009-0001-1870-6859","affiliations":[{"raw_affiliation_string":"IIIT Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Swarang Joshi","orcid":"https://orcid.org/0009-0002-3609-4523"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Swarang Joshi","raw_affiliation_strings":["IIIT Hyderabad, Hyderabad, India"],"raw_orcid":"https://orcid.org/0009-0002-3609-4523","affiliations":[{"raw_affiliation_string":"IIIT Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Monojit Choudhury","orcid":"https://orcid.org/0000-0001-7473-7839"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Monojit Choudhury","raw_affiliation_strings":["MBZUAI, Abu Dhabi, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0001-7473-7839","affiliations":[{"raw_affiliation_string":"MBZUAI, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027543950","display_name":"Ponnurangam Kumaraguru","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ponnurangam Kumaraguru","raw_affiliation_strings":["IIIT Hyderabad, Hyderabad, India"],"raw_orcid":"https://orcid.org/0000-0001-5082-2078","affiliations":[{"raw_affiliation_string":"IIIT Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013675579","display_name":"Manish Shrivastava","orcid":"https://orcid.org/0000-0001-8705-6637"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Manish Shrivastava","raw_affiliation_strings":["IIIT Hyderabad, Hyderabad, India"],"raw_orcid":"https://orcid.org/0000-0001-8705-6637","affiliations":[{"raw_affiliation_string":"IIIT Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5083888032"],"corresponding_institution_ids":["https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17221963,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"199","last_page":"207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3212999999523163,"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":0.3212999999523163,"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":0.13230000436306,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.1128000020980835,"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/transfer-of-learning","display_name":"Transfer of learning","score":0.6018000245094299},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.5737000107765198},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5321999788284302},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4878999888896942},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.46369999647140503},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42149999737739563},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.41690000891685486},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.40549999475479126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7925999760627747},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6018000245094299},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.5737000107765198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5489000082015991},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5321999788284302},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48399999737739563},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.46369999647140503},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4336000084877014},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42149999737739563},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.34779998660087585},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30730000138282776},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.2883000075817108},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2825999855995178}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3799830.3799852","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799830.3799852","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM IKDD International Conference on Data Science","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.19782","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.19782","pdf_url":"https://arxiv.org/pdf/2510.19782","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2510.19782","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.19782","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/3799830.3799852","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799830.3799852","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM IKDD International Conference on Data Science","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,51,158],"study":[1],"model":[2],"merging":[3,101],"as":[4,151],"a":[5,16,152],"practical":[6],"alternative":[7],"to":[8,30,134],"standard":[9],"adaptation":[10,161],"for":[11,127,155,163,177],"code-mixed":[12,28,128,149],"NLP.":[13],"Starting":[14],"from":[15,132],"multilingual":[17],"base":[18,41],"model,":[19,42],"we":[20],"(i)":[21],"perform":[22],"continued":[23],"pre-training":[24],"(CPT)":[25],"on":[26,47,55],"unlabeled":[27,103],"text":[29],"obtain":[31],"an":[32],"adapted":[33],"checkpoint,":[34],"(ii)":[35],"merge":[36],"this":[37,53],"checkpoint":[38],"with":[39,112,160],"the":[40],"and":[43,59,65,70,79,92,119,171,174,180],"(iii)":[44],"fine-tune":[45],"(FT)":[46],"downstream":[48],"task":[49],"data.":[50],"evaluate":[52],"approach":[54],"sentence":[56],"classification":[57],"(sentiment":[58],"hate":[60],"speech)":[61],"in":[62],"English-Hindi":[63],"(En-Hi)":[64],"English-Spanish":[66],"(En-Es)":[67],"using":[68],"XLM-R":[69],"Llama-3.2-1B.":[71],"Merged":[72],"models":[73],"consistently":[74],"outperform":[75,141],"both":[76],"full":[77,90],"fine-tuning":[78,91],"CPT":[80,96,108],"\u2192":[81,97],"FT,":[82,98],"yielding":[83],"gains":[84],"of":[85,124],"2\u20135":[86],"F1":[87],"points":[88],"over":[89,95],"\u223c":[93],"1\u20132":[94],"suggesting":[99],"that":[100],"exploits":[102],"data":[104,165],"more":[105],"effectively":[106],"than":[107],"alone.":[109],"Zero-/few-shot":[110],"prompting":[111],"larger":[113,181],"LLMs":[114],"(e.g.,":[115,139],"Llama-3.3-70B)":[116],"trails":[117],"fine-tuned":[118],"merged":[120,137],"checkpoints,":[121],"highlighting":[122],"limits":[123],"in-context":[125],"learning":[126],"inputs.":[129],"Cross-pair":[130],"transfer":[131],"En\u2013Hi":[133],"En\u2013Ta/Ml":[135],"shows":[136],"checkpoints":[138],"TV/TIES)":[140],"monolingual":[142],"baselines":[143],"(0.65\u20130.68":[144],"vs.":[145],"0.61\u20130.63":[146],"F1),":[147],"confirming":[148],"knowledge":[150],"superior":[153],"substrate":[154],"low-resource":[156],"pairs.":[157],"conclude":[159],"recipes":[162],"common":[164],"regimes":[166],"(labeled":[167],"only;":[168],"labeled+unlabeled;":[169],"transfer-only)":[170],"discuss":[172],"limitations":[173],"scaling":[175],"considerations":[176],"broader":[178],"tasks":[179],"models.":[182]},"counts_by_year":[],"updated_date":"2026-04-26T06:01:38.667478","created_date":"2025-10-24T00:00:00"}