{"id":"https://openalex.org/W7204851982","doi":"https://doi.org/10.48550/arxiv.2608.27753","title":"What Can Low Resource Languages Learn From Each Other?","display_name":"What Can Low Resource Languages Learn From Each Other?","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7204851982","doi":"https://doi.org/10.48550/arxiv.2608.27753"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.27753","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27753","pdf_url":"https://arxiv.org/pdf/2608.27753","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.27753","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033168738","display_name":"P. Achyuth","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P, Achyuth","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090374672","display_name":"Kahaan Shah","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shah, Kahaan","raw_affiliation_strings":["IIT Delhi , New Delhi , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Delhi , New Delhi , India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125219111","display_name":"Chetan Arora","orcid":"https://orcid.org/0000-0003-1466-7386","observed_orcids":["https://orcid.org/0000-0003-1466-7386"]},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arora, Chetan","raw_affiliation_strings":["IIT Delhi , New Delhi , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Delhi , New Delhi , India","institution_ids":["https://openalex.org/I68891433"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9955999851226807,"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"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9955999851226807,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.0017000000225380063,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0010000000474974513,"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/optical-character-recognition","display_name":"optical character recognition","score":0.8500000238418579},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.8389999866485596},{"id":"https://openalex.org/keywords/multilingual-ocr","display_name":"multilingual OCR","score":0.5260000228881836},{"id":"https://openalex.org/keywords/data-efficient-fine-tuning","display_name":"data-efficient fine-tuning","score":0.6370000243186951},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.5960000157356262},{"id":"https://openalex.org/keywords/indic-scripts","display_name":"Indic scripts","score":0.5350000262260437},{"id":"https://openalex.org/keywords/word-recognition","display_name":"word recognition","score":0.46000000834465027},{"id":"https://openalex.org/keywords/digital-divide","display_name":"digital divide","score":0.5339999794960022},{"id":"https://openalex.org/keywords/psmc","display_name":"PSMC","score":0.6330000162124634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7545999884605408},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.7328000068664551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.551800012588501},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5386000275611877},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5349000096321106},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.513700008392334},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5128999948501587},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4099999964237213},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C2778701210","wikidata":"https://www.wikidata.org/wiki/Q28130034","display_name":"Constructive","level":3,"score":0.4000000059604645},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3303000032901764},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.2985000014305115},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C2778473407","wikidata":"https://www.wikidata.org/wiki/Q1459574","display_name":"Compendium","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.27753","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27753","pdf_url":"https://arxiv.org/pdf/2608.27753","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.2608.27753","doi":"https://doi.org/10.48550/arxiv.2608.27753","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.27753","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:2608.27753","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27753","pdf_url":"https://arxiv.org/pdf/2608.27753","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204851982.pdf","grobid_xml":"https://content.openalex.org/works/W7204851982.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2785383245","https://openalex.org/W2956161426","https://openalex.org/W3003645575","https://openalex.org/W3003711889","https://openalex.org/W3184921135","https://openalex.org/W3198566525","https://openalex.org/W4382202677","https://openalex.org/W4392911146","https://openalex.org/W4400519201","https://openalex.org/W4416055645","https://openalex.org/W4416780398","https://openalex.org/W7077911270"],"related_works":["https://openalex.org/W7131434285","https://openalex.org/W7204888958","https://openalex.org/W4405715760","https://openalex.org/W4414253760","https://openalex.org/W7197673002","https://openalex.org/W3128424785","https://openalex.org/W7139913936","https://openalex.org/W7166878530","https://openalex.org/W4411630264","https://openalex.org/W3168641112"],"abstract_inverted_index":{"Despite":[0],"the":[1,18,21,27,49,103,196],"rapid":[2],"advancement":[3],"of":[4,20,30,94],"Vision-Language":[5],"Models":[6],"(VLMs),":[7],"their":[8],"linguistic":[9],"reach":[10,77],"remains":[11],"largely":[12],"confined":[13],"to":[14,98,148],"high-resource":[15,141],"languages,":[16],"leaving":[17],"majority":[19],"world's":[22],"7,000+":[23],"living":[24],"languages":[25],"on":[26,128],"wrong":[28],"side":[29],"a":[31,78,85,123,129,140,153,172,201,211],"growing":[32],"digital":[33],"divide.":[34],"This":[35],"disparity":[36],"is":[37],"especially":[38],"pronounced":[39],"in":[40,61,88,176,195],"Optical":[41],"Character":[42],"Recognition":[43,178],"(OCR),":[44],"where":[45],"low-resource":[46],"scripts":[47,164],"lack":[48],"massive":[50],"datasets":[51,221],"required":[52],"for":[53,214],"traditional":[54],"scaling":[55],"laws.":[56],"We":[57],"investigate":[58],"OCR":[59],"adaptation":[60],"extreme":[62],"data-scarce":[63],"regimes":[64],"(<10K":[65],"real":[66],"and":[67,121,220],"<250K":[68],"synthetic":[69],"images),":[70],"demonstrating":[71],"that":[72,126,169,192,205],"conventional":[73],"fine-tuning":[74],"strategies":[75],"often":[76],"performance":[79],"ceiling.":[80],"Our":[81,133,189],"key":[82],"finding":[83],"reveals":[84],"structural":[86],"inefficiency":[87],"language-specific":[89,137],"adaptation:":[90],"while":[91],"higher":[92],"layers":[93,105],"specialized":[95],"models":[96,184],"diverge":[97],"capture":[99],"unique":[100],"script":[101],"nuances,":[102],"lower":[104],"learn":[106],"redundant,":[107],"highly":[108],"similar":[109],"features.":[110],"Motivated":[111],"by":[112],"this":[113],"observation,":[114],"we":[115],"propose":[116],"PSMC":[117,170],"(Pre-train,":[118],"Specialize,":[119],"Merge,":[120],"Co-train),":[122],"data-efficient":[124],"framework":[125],"capitalizes":[127],"cross-script":[130],"\"transfer":[131],"effect\".":[132],"approach":[134],"first":[135],"derives":[136],"experts":[138,151],"from":[139],"base":[142],"model,":[143],"then":[144],"employs":[145],"task":[146],"arithmetic":[147],"fuse":[149],"these":[150],"into":[152],"unified,":[154],"high-performance":[155],"multilingual":[156],"back-":[157],"bone.":[158],"Extensive":[159],"evaluation":[160],"across":[161],"10":[162],"Indian":[163],"(supporting":[165],"20+":[166],"languages)":[167],"shows":[168],"achieves":[171],"~2%":[173],"average":[174],"improvement":[175],"Word":[177],"Rate":[179],"(WRR)":[180],"over":[181],"individual":[182],"specialist":[183],"without":[185],"increasing":[186],"parameter":[187],"count.":[188],"results":[190],"indicate":[191],"joint":[193],"training":[194],"merged":[197],"latent":[198],"space":[199],"facilitates":[200],"constructive":[202],"knowledge":[203],"transfer":[204],"benefits":[206],"all":[207],"constituent":[208],"scripts,":[209],"providing":[210],"scalable":[212],"pathway":[213],"inclusive":[215],"VLM":[216],"development.":[217],"Source":[218],"code":[219],"will":[222],"be":[223],"released":[224],"post":[225],"publication.":[226]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-01T00:00:00"}