{"id":"https://openalex.org/W4386721790","doi":"https://doi.org/10.48550/arxiv.2309.06085","title":"BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models","display_name":"BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models","publication_year":2023,"publication_date":"2023-09-12","ids":{"openalex":"https://openalex.org/W4386721790","doi":"https://doi.org/10.48550/arxiv.2309.06085"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2309.06085","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.06085","pdf_url":"https://arxiv.org/pdf/2309.06085","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/2309.06085","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038370332","display_name":"Wei Qi Leong","orcid":"https://orcid.org/0009-0002-0645-1112","observed_orcids":["https://orcid.org/0009-0002-0645-1112"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I4405253446","display_name":"AI Singapore","ror":"https://ror.org/00ntacr26","country_code":"SG","type":"government","lineage":["https://openalex.org/I4405253446"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Leong, Wei Qi","raw_affiliation_strings":["AI Singapore National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Singapore National University of Singapore","institution_ids":["https://openalex.org/I165932596","https://openalex.org/I4405253446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008355407","display_name":"Jian Gang Ngui","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I4405253446","display_name":"AI Singapore","ror":"https://ror.org/00ntacr26","country_code":"SG","type":"government","lineage":["https://openalex.org/I4405253446"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ngui, Jian Gang","raw_affiliation_strings":["AI Singapore National University of Singapore Department of Linguistics ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Singapore National University of Singapore Department of Linguistics ,","institution_ids":["https://openalex.org/I165932596","https://openalex.org/I4405253446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034411908","display_name":"Yosephine Susanto","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Susanto, Yosephine","raw_affiliation_strings":["AI","Singapore National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI","institution_ids":[]},{"raw_affiliation_string":"Singapore National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062797041","display_name":"Hamsawardhini Rengarajan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rengarajan, Hamsawardhini","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062180077","display_name":"Kengatharaiyer Sarveswaran","orcid":"https://orcid.org/0000-0003-1579-0597","observed_orcids":["https://orcid.org/0000-0003-1579-0597"]},"institutions":[{"id":"https://openalex.org/I198412587","display_name":"University of Jaffna","ror":"https://ror.org/02fwjgw17","country_code":"LK","type":"education","lineage":["https://openalex.org/I198412587"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Sarveswaran, Kengatharaiyer","raw_affiliation_strings":["Department of Computer Science , University of Jaffna"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Jaffna","institution_ids":["https://openalex.org/I198412587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086528347","display_name":"William Chandra Tjhi","orcid":"https://orcid.org/0009-0009-9861-3545","observed_orcids":["https://orcid.org/0009-0009-9861-3545"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I4405253446","display_name":"AI Singapore","ror":"https://ror.org/00ntacr26","country_code":"SG","type":"government","lineage":["https://openalex.org/I4405253446"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tjhi, William Chandra","raw_affiliation_strings":["AI Singapore National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Singapore National University of Singapore","institution_ids":["https://openalex.org/I165932596","https://openalex.org/I4405253446"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"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/T10028","display_name":"Topic Modeling","score":0.7167999744415283,"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":0.7167999744415283,"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":0.2712000012397766,"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":0.002400000113993883,"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/bhasa","display_name":"Bhasa","score":0.7940000295639038},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.675000011920929},{"id":"https://openalex.org/keywords/southeast-asian-languages","display_name":"Southeast Asian languages","score":0.7440000176429749},{"id":"https://openalex.org/keywords/cultural-representation","display_name":"cultural representation","score":0.6129999756813049},{"id":"https://openalex.org/keywords/cultural-sensitivity","display_name":"cultural sensitivity","score":0.9879999756813049},{"id":"https://openalex.org/keywords/indonesian","display_name":"Indonesian","score":0.6470000147819519},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.9549999833106995},{"id":"https://openalex.org/keywords/thai","display_name":"Thai","score":0.9940000176429749},{"id":"https://openalex.org/keywords/tamil","display_name":"Tamil language","score":1.0},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"natural language understanding","score":0.8360000252723694},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"natural language generation","score":0.9660000205039978},{"id":"https://openalex.org/keywords/natural-language-reasoning","display_name":"natural language reasoning","score":0.8830000162124634},{"id":"https://openalex.org/keywords/gpt-4-comparison","display_name":"GPT-4 comparison","score":0.7799999713897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5623685121536255},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5312485694885254},{"id":"https://openalex.org/C140688305","wikidata":"https://www.wikidata.org/wiki/Q5885","display_name":"Tamil","level":2,"score":0.5011641979217529},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.44982144236564636},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.438279390335083},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.435623437166214},{"id":"https://openalex.org/C2779207338","wikidata":"https://www.wikidata.org/wiki/Q9240","display_name":"Indonesian","level":2,"score":0.4160707890987396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37882012128829956},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.15779364109039307},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2309.06085","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.06085","pdf_url":"https://arxiv.org/pdf/2309.06085","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.2309.06085","doi":"https://doi.org/10.48550/arxiv.2309.06085","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2309.06085","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:2309.06085","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.06085","pdf_url":"https://arxiv.org/pdf/2309.06085","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":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386721790.pdf","grobid_xml":"https://content.openalex.org/works/W4386721790.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4407806697","https://openalex.org/W7166871831","https://openalex.org/W4405033903","https://openalex.org/W4411120180","https://openalex.org/W4417142613","https://openalex.org/W7163381156","https://openalex.org/W4389326213","https://openalex.org/W4416529434","https://openalex.org/W7212174447","https://openalex.org/W4401201935"],"abstract_inverted_index":{"The":[0,230],"rapid":[1],"development":[2],"of":[3,11,20,36,105,162,180,185,201],"Large":[4],"Language":[5,86],"Models":[6],"(LLMs)":[7],"and":[8,23,29,45,64,91,111,113,125,141,143,148,152,206,219,225],"the":[9,18,33,103,133,153,163,168,178,183,209,228],"emergence":[10],"novel":[12],"abilities":[13],"with":[14,193],"scale":[15],"have":[16],"necessitated":[17],"construction":[19],"holistic,":[21],"diverse":[22],"challenging":[24],"benchmarks":[25,38],"such":[26],"as":[27,173],"HELM":[28],"BIG-bench.":[30],"However,":[31],"at":[32,167],"moment,":[34,169],"most":[35],"these":[37],"focus":[39],"only":[40,136,145],"on":[41,191],"performance":[42],"in":[43,55,70,182,198,208,217,227],"English":[44],"evaluations":[46],"that":[47,101,119],"include":[48,146],"Southeast":[49],"Asian":[50],"(SEA)":[51],"languages":[52],"are":[53],"few":[54],"number.":[56],"We":[57],"therefore":[58],"propose":[59],"BHASA,":[60],"a":[61,78,97,115,174,215],"holistic":[62],"linguistic":[63,98,106,202],"cultural":[65,116,123,154,204],"evaluation":[66],"suite":[67],"for":[68,121,137,150,232],"LLMs":[69,166,181],"SEA":[71,186,211],"languages.":[72,187,212],"It":[73],"comprises":[74],"three":[75],"components:":[76],"(1)":[77],"NLP":[79,134],"benchmark":[80,135],"covering":[81],"eight":[82],"tasks":[83],"across":[84],"Natural":[85],"Understanding":[87],"(NLU),":[88],"Generation":[89],"(NLG)":[90],"Reasoning":[92],"(NLR)":[93],"tasks,":[94],"(2)":[95],"LINDSEA,":[96],"diagnostic":[99],"toolkit":[100],"spans":[102],"gamut":[104],"phenomena":[107],"including":[108],"syntax,":[109],"semantics":[110],"pragmatics,":[112],"(3)":[114],"diagnostics":[117,155],"dataset":[118],"probes":[120],"both":[122],"representation":[124,205],"sensitivity.":[126],"For":[127],"this":[128,233],"preliminary":[129],"effort,":[130],"we":[131,144,170],"implement":[132],"Indonesian,":[138],"Vietnamese,":[139],"Thai":[140],"Tamil,":[142],"Indonesian":[147],"Tamil":[149],"LINDSEA":[151],"dataset.":[156],"As":[157],"GPT-4":[158,192],"is":[159,214],"purportedly":[160],"one":[161],"best-performing":[164],"multilingual":[165],"use":[171],"it":[172,196],"yardstick":[175],"to":[176,222],"gauge":[177],"capabilities":[179],"context":[184],"Our":[188],"initial":[189],"experiments":[190],"BHASA":[194,213],"find":[195],"lacking":[197],"various":[199],"aspects":[200],"capabilities,":[203],"sensitivity":[207],"targeted":[210],"work":[216],"progress":[218],"will":[220],"continue":[221],"be":[223,236],"improved":[224],"expanded":[226],"future.":[229],"repository":[231],"paper":[234],"can":[235],"found":[237],"at:":[238],"https://github.com/aisingapore/BHASA":[239]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-10-10T09:11:00.788812","created_date":"2023-09-14T00:00:00"}