{"id":"https://openalex.org/W6929269293","doi":"https://doi.org/10.48550/arxiv.2503.18288","title":"TFD: A Comprehensive Structured Tibetan Foundation Dataset for Low-Resource Language Processing and Large-Scale Modeling","display_name":"TFD: A Comprehensive Structured Tibetan Foundation Dataset for Low-Resource Language Processing and Large-Scale Modeling","publication_year":2025,"publication_date":"2025-03-24","ids":{"openalex":"https://openalex.org/W6929269293","doi":"https://doi.org/10.48550/arxiv.2503.18288"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2503.18288","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2503.18288","pdf_url":"https://arxiv.org/pdf/2503.18288","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","license_id":"https://openalex.org/licenses/cc-by","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/2503.18288","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5143165951","display_name":"Cheng Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Gao, Fan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050819315","display_name":"Nyima Tashi","orcid":"https://orcid.org/0000-0001-9288-6600","observed_orcids":["https://orcid.org/0000-0001-9288-6600"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tashi, Nyima","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100696596","display_name":"Yutong Liu","orcid":"https://orcid.org/0000-0001-6507-7090","observed_orcids":["https://orcid.org/0000-0001-6507-7090"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yutong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143259915","display_name":"Yadi Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yadi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135060505","display_name":"Wenbin WEI","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Wenbin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143179642","display_name":"Xiangxiang Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiangxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5143319747","display_name":"Yongbin Yu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Yongbin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":true,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6083999872207642,"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":0.6083999872207642,"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":0.3788999915122986,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.003800000064074993,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/tibetan-language","display_name":"Tibetan language","score":0.9409999847412109},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7049999833106995},{"id":"https://openalex.org/keywords/instruction-tuning","display_name":"instruction tuning","score":0.9700000286102295},{"id":"https://openalex.org/keywords/safety-alignment","display_name":"safety alignment","score":0.9860000014305115},{"id":"https://openalex.org/keywords/preference-optimization","display_name":"preference optimization","score":0.996999979019165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6779999732971191},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.47200000286102295},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45660001039505005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4047999978065491},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3853999972343445},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3716999888420105},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2503.18288","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2503.18288","pdf_url":"https://arxiv.org/pdf/2503.18288","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.18288","doi":"https://doi.org/10.48550/arxiv.2503.18288","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.18288","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.18288","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2503.18288","pdf_url":"https://arxiv.org/pdf/2503.18288","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","license_id":"https://openalex.org/licenses/cc-by","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417101759","https://openalex.org/W4416228965","https://openalex.org/W4405592778","https://openalex.org/W6979357603","https://openalex.org/W4405123407","https://openalex.org/W4411144143","https://openalex.org/W4386977805","https://openalex.org/W4417034881","https://openalex.org/W4280503145","https://openalex.org/W7163913639"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4,21],"achieved":[5],"remarkable":[6],"success":[7],"in":[8,13],"high-resource":[9],"languages,":[10],"yet":[11],"progress":[12],"Tibetan":[14,58,74,105,118,165],"remains":[15],"severely":[16],"constrained.":[17],"While":[18],"recent":[19],"efforts":[20],"begun":[22],"to":[23,154],"address":[24],"pre-training":[25],"data":[26,149,169],"scarcity":[27],"for":[28,92],"Tibetan,":[29],"a":[30,81,146],"more":[31],"fundamental":[32],"gap":[33],"persists:":[34],"no":[35],"existing":[36],"resource":[37],"supports":[38],"the":[39,57,62,102,114,159],"complete":[40,148],"LLM":[41],"development":[42,160],"pipeline,":[43],"spanning":[44],"pre-training,":[45],"instruction":[46,93],"tuning,":[47,94],"safety":[48,95],"alignment,":[49,96],"preference":[50,98],"optimization,":[51,99],"and":[52,66,97,100,130,158,168],"reasoning":[53],"supervision.":[54],"We":[55,108,151],"introduce":[56],"Foundation":[59],"Dataset":[60],"(TFD),":[61],"first":[63,103],"structured,":[64],"large-scale,":[65],"expert-curated":[67],"dataset":[68],"covering":[69],"all":[70],"key":[71],"stages":[72],"of":[73,84,117,161],"large":[75],"language":[76,139],"modeling.":[77],"TFD":[78,153],"comprises":[79],"TIBSTC,":[80],"unified":[82],"corpus":[83],"over":[85,123],"11":[86],"billion":[87],"tokens":[88],"with":[89],"curated":[90],"sub-datasets":[91],"TIBSTC-CoT,":[101],"large-scale":[104],"chain-of-thought":[106],"dataset.":[107],"demonstrate":[109],"its":[110],"utility":[111],"by":[112],"training":[113],"Sun-Shine":[115],"family":[116],"LLMs,":[119],"achieving":[120],"substantial":[121],"improvements":[122],"strong":[124],"baselines":[125],"on":[126],"understanding,":[127],"safety,":[128],"reasoning,":[129],"generation":[131],"benchmarks.":[132],"These":[133],"results":[134],"underscore":[135],"that":[136],"advancing":[137],"low-resource":[138],"modeling":[140],"requires":[141],"not":[142],"only":[143],"scale,":[144],"but":[145],"structurally":[147],"ecosystem.":[150],"release":[152],"facilitate":[155],"reproducible":[156],"research":[157],"robust,":[162],"culturally":[163],"aligned":[164],"LLMs.":[166],"Code":[167],"are":[170],"available":[171],"at":[172],"https://github.com/Vicentvankor/sun-shine.":[173]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}