{"id":"https://openalex.org/W3180299705","doi":"https://doi.org/10.1145/3727339","title":"A Primer on Pretrained Multilingual Language Models","display_name":"A Primer on Pretrained Multilingual Language Models","publication_year":2025,"publication_date":"2025-04-01","ids":{"openalex":"https://openalex.org/W3180299705","doi":"https://doi.org/10.1145/3727339","mag":"3180299705"},"language":"en","primary_location":{"id":"doi:10.1145/3727339","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3727339","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3727339","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3727339","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078774993","display_name":"Sumanth Doddapaneni","orcid":"https://orcid.org/0000-0003-4248-646X"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sumanth Doddapaneni","raw_affiliation_strings":["Computer Science and Engineering, IIT Madras, Chennai, India"],"raw_orcid":"https://orcid.org/0000-0003-4248-646X","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, IIT Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gowtham Ramesh","orcid":"https://orcid.org/0000-0002-4976-0700"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gowtham Ramesh","raw_affiliation_strings":["Advanced Micro Devices Inc, Santa Clara, United States"],"raw_orcid":"https://orcid.org/0000-0002-4976-0700","affiliations":[{"raw_affiliation_string":"Advanced Micro Devices Inc, Santa Clara, United States","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050036814","display_name":"Mitesh M. Khapra","orcid":"https://orcid.org/0009-0008-3687-9922"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mitesh Khapra","raw_affiliation_strings":["Wadhwani School of Data Science & AI, Indian Institute of Technology Madras, Chennai, India"],"raw_orcid":"https://orcid.org/0009-0008-3687-9922","affiliations":[{"raw_affiliation_string":"Wadhwani School of Data Science & AI, Indian Institute of Technology Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108009533","display_name":"Anoop Kunchukuttan","orcid":"https://orcid.org/0009-0007-3143-9875"},"institutions":[{"id":"https://openalex.org/I4210162141","display_name":"Microsoft (India)","ror":"https://ror.org/04ww0w091","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210162141"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anoop Kunchukuttan","raw_affiliation_strings":["Microsoft India R&D Pvt Ltd, Hyderabad, India"],"raw_orcid":"https://orcid.org/0009-0007-3143-9875","affiliations":[{"raw_affiliation_string":"Microsoft India R&D Pvt Ltd, Hyderabad, India","institution_ids":["https://openalex.org/I4210162141"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101614266","display_name":"Pratyush Kumar","orcid":"https://orcid.org/0000-0002-8732-0183"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pratyush Kumar","raw_affiliation_strings":["Computer Science and Engineering, IIT Madras, Chennai, India"],"raw_orcid":"https://orcid.org/0000-0002-8732-0183","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, IIT Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.7382,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.98083618,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"57","issue":"9","first_page":"1","last_page":"39"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9948999881744385,"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/primer","display_name":"Primer (cosmetics)","score":0.7419064044952393},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.607014536857605},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5576267838478088},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5124738812446594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4041805863380432},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.09559834003448486},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08579835295677185}],"concepts":[{"id":"https://openalex.org/C2777563447","wikidata":"https://www.wikidata.org/wiki/Q7243397","display_name":"Primer (cosmetics)","level":2,"score":0.7419064044952393},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.607014536857605},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5576267838478088},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5124738812446594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4041805863380432},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.09559834003448486},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08579835295677185},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3727339","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3727339","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3727339","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},{"id":"mag:3180299705","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2107.00676.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"doi:10.1145/3727339","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3727339","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3727339","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8500000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3180299705.pdf"},"referenced_works_count":190,"referenced_works":["https://openalex.org/W131533222","https://openalex.org/W1516184288","https://openalex.org/W2006969979","https://openalex.org/W2121879602","https://openalex.org/W2126725946","https://openalex.org/W2144578941","https://openalex.org/W2148708890","https://openalex.org/W2156985047","https://openalex.org/W2251939518","https://openalex.org/W2489487449","https://openalex.org/W2525778437","https://openalex.org/W2538358357","https://openalex.org/W2558906580","https://openalex.org/W2560674852","https://openalex.org/W2607303097","https://openalex.org/W2742155240","https://openalex.org/W2747329762","https://openalex.org/W2750779823","https://openalex.org/W2769280657","https://openalex.org/W2842511635","https://openalex.org/W2891555348","https://openalex.org/W2915429162","https://openalex.org/W2923014074","https://openalex.org/W2946794439","https://openalex.org/W2950733326","https://openalex.org/W2952638691","https://openalex.org/W2962784628","https://openalex.org/W2962869940","https://openalex.org/W2963211188","https://openalex.org/W2963216553","https://openalex.org/W2963223306","https://openalex.org/W2963250244","https://openalex.org/W2963310665","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963633299","https://openalex.org/W2963721344","https://openalex.org/W2963846996","https://openalex.org/W2964303773","https://openalex.org/W2964308564","https://openalex.org/W2965373594","https://openalex.org/W2970193165","https://openalex.org/W2970752815","https://openalex.org/W2970850076","https://openalex.org/W2970854433","https://openalex.org/W2971207485","https://openalex.org/W2971863715","https://openalex.org/W2973088264","https://openalex.org/W2981852735","https://openalex.org/W2983040767","https://openalex.org/W2983836503","https://openalex.org/W2985620815","https://openalex.org/W2986154550","https://openalex.org/W2987270981","https://openalex.org/W2989276524","https://openalex.org/W2992787485","https://openalex.org/W2994885767","https://openalex.org/W2994928925","https://openalex.org/W2995015695","https://openalex.org/W2995118574","https://openalex.org/W2995647371","https://openalex.org/W2996822578","https://openalex.org/W2998215494","https://openalex.org/W3001434439","https://openalex.org/W3011411500","https://openalex.org/W3011574394","https://openalex.org/W3016562905","https://openalex.org/W3016973796","https://openalex.org/W3021534198","https://openalex.org/W3021766370","https://openalex.org/W3022408339","https://openalex.org/W3022583179","https://openalex.org/W3023133114","https://openalex.org/W3030175377","https://openalex.org/W3030394039","https://openalex.org/W3032388710","https://openalex.org/W3032532958","https://openalex.org/W3034469191","https://openalex.org/W3034949522","https://openalex.org/W3034999214","https://openalex.org/W3035032094","https://openalex.org/W3035137491","https://openalex.org/W3035390927","https://openalex.org/W3035463087","https://openalex.org/W3035497479","https://openalex.org/W3035524453","https://openalex.org/W3035547806","https://openalex.org/W3042381743","https://openalex.org/W3042711927","https://openalex.org/W3045462440","https://openalex.org/W3051275803","https://openalex.org/W3085139254","https://openalex.org/W3087873698","https://openalex.org/W3088382025","https://openalex.org/W3090350559","https://openalex.org/W3093721400","https://openalex.org/W3095349973","https://openalex.org/W3097879195","https://openalex.org/W3098466758","https://openalex.org/W3098604850","https://openalex.org/W3098886914","https://openalex.org/W3099004917","https://openalex.org/W3099771192","https://openalex.org/W3099793224","https://openalex.org/W3099919888","https://openalex.org/W3100198908","https://openalex.org/W3100308117","https://openalex.org/W3101498587","https://openalex.org/W3102455836","https://openalex.org/W3102483398","https://openalex.org/W3103490574","https://openalex.org/W3104033643","https://openalex.org/W3104329353","https://openalex.org/W3104723404","https://openalex.org/W3104881680","https://openalex.org/W3105190698","https://openalex.org/W3105220303","https://openalex.org/W3105421296","https://openalex.org/W3105813095","https://openalex.org/W3107826490","https://openalex.org/W3112302586","https://openalex.org/W3115224631","https://openalex.org/W3115903740","https://openalex.org/W3117614783","https://openalex.org/W3118106810","https://openalex.org/W3118415754","https://openalex.org/W3118485687","https://openalex.org/W3118832851","https://openalex.org/W3118942129","https://openalex.org/W3126822054","https://openalex.org/W3128424785","https://openalex.org/W3152609875","https://openalex.org/W3152879179","https://openalex.org/W3153266325","https://openalex.org/W3155609600","https://openalex.org/W3168210179","https://openalex.org/W3169425228","https://openalex.org/W3169483174","https://openalex.org/W3171975879","https://openalex.org/W3173360659","https://openalex.org/W3173894143","https://openalex.org/W3175898847","https://openalex.org/W3176765167","https://openalex.org/W3183859557","https://openalex.org/W3190572136","https://openalex.org/W3214161538","https://openalex.org/W3214173179","https://openalex.org/W4206471589","https://openalex.org/W4224247062","https://openalex.org/W4224308101","https://openalex.org/W4236950558","https://openalex.org/W4239019441","https://openalex.org/W4246708511","https://openalex.org/W4252110927","https://openalex.org/W4285077564","https://openalex.org/W4288089799","https://openalex.org/W4299527668","https://openalex.org/W4308760226","https://openalex.org/W4311642023","https://openalex.org/W4322718191","https://openalex.org/W4366327277","https://openalex.org/W4376312459","https://openalex.org/W4377121468","https://openalex.org/W4378505287","https://openalex.org/W4384264777","https://openalex.org/W4384918448","https://openalex.org/W4385565879","https://openalex.org/W4385570009","https://openalex.org/W4385570349","https://openalex.org/W4385570522","https://openalex.org/W4385571031","https://openalex.org/W4385572376","https://openalex.org/W4385572438","https://openalex.org/W4385572860","https://openalex.org/W4385574330","https://openalex.org/W4389326213","https://openalex.org/W4389519232","https://openalex.org/W4389925930","https://openalex.org/W4389984105","https://openalex.org/W4390573437","https://openalex.org/W4391156274","https://openalex.org/W4391244633","https://openalex.org/W4393727555","https://openalex.org/W4402671557","https://openalex.org/W6739901393","https://openalex.org/W6771823989","https://openalex.org/W6779771702","https://openalex.org/W6779941907","https://openalex.org/W6783267081","https://openalex.org/W6793873773"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2375570161","https://openalex.org/W2371958667","https://openalex.org/W4401150813","https://openalex.org/W2390279801","https://openalex.org/W2333833013","https://openalex.org/W4391913857","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Multilingual":[0],"Language":[1],"Models":[2],"(MLLMs)":[3],"such":[4],"as":[5,14],"mBERT,":[6],"XLM,":[7],"XLM-R,":[8],"and":[9,66,81,95],"the":[10,20,73,86,98,119,123],"like,":[11],"have":[12],"emerged":[13,39],"a":[15,25,40,51,61],"viable":[16],"option":[17],"for":[18,68],"bringing":[19],"power":[21],"of":[22,28,43,54,64,75,102,127,141],"pretraining":[23],"to":[24,104,130],"large":[26,41,52],"number":[27,53],"languages.":[29,113],"Given":[30],"their":[31,106],"success":[32],"in":[33,45],"zero-shot":[34,79],"transfer":[35],"learning,":[36],"there":[37],"has":[38],"body":[42],"work":[44],"(i)":[46],"building":[47],"bigger":[48],"MLLMs":[49,76,103],"covering":[50,60,122],"languages,":[55],"(ii)":[56],"creating":[57],"exhaustive":[58],"benchmarks":[59],"wider":[62],"variety":[63],"tasks":[65],"languages":[67],"evaluating":[69],"MLLMs,":[70,94],"(iii)":[71],"analysing":[72],"performance":[74,107],"on":[77,108,133],"monolingual,":[78],"cross-lingual":[80],"bilingual":[82],"tasks,":[83],"(iv)":[84],"understanding":[85],"universal":[87],"language":[88],"patterns":[89],"(if":[90],"any)":[91],"learnt":[92],"by":[93],"(v)":[96],"augmenting":[97],"(often)":[99],"limited":[100],"capacity":[101],"improve":[105],"seen":[109],"or":[110],"even":[111],"unseen":[112],"In":[114],"this":[115],"survey,":[116,135],"we":[117,136],"review":[118],"existing":[120],"literature":[121],"above":[124],"broad":[125],"areas":[126],"research":[128],"pertaining":[129],"MLLMs.":[131],"Based":[132],"our":[134],"recommend":[137],"some":[138],"promising":[139],"directions":[140],"future":[142],"research.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}