{"id":"https://openalex.org/W4416035308","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1706","title":"DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultural Text Adaptation in Indian Context","display_name":"DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultural Text Adaptation in Indian Context","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035308","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1706"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1706","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1706","pdf_url":"https://aclanthology.org/2025.emnlp-main.1706.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1706.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088920217","display_name":"Pramit Sahoo","orcid":null},"institutions":[{"id":"https://openalex.org/I55664587","display_name":"Indian Institute of Chemical Technology","ror":"https://ror.org/040dky007","country_code":"IN","type":"facility","lineage":["https://openalex.org/I2799351866","https://openalex.org/I4210134808","https://openalex.org/I55664587","https://openalex.org/I66760702"]},{"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":"Pramit Sahoo","raw_affiliation_strings":["Natural Language and Information Processing Lab (NLIP ) Indian Institute of Technology Hyderabad Hyderabad , India"],"affiliations":[{"raw_affiliation_string":"Natural Language and Information Processing Lab (NLIP ) Indian Institute of Technology Hyderabad Hyderabad , India","institution_ids":["https://openalex.org/I65181880","https://openalex.org/I55664587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016534605","display_name":"Maharaj Brahma","orcid":null},"institutions":[{"id":"https://openalex.org/I55664587","display_name":"Indian Institute of Chemical Technology","ror":"https://ror.org/040dky007","country_code":"IN","type":"facility","lineage":["https://openalex.org/I2799351866","https://openalex.org/I4210134808","https://openalex.org/I55664587","https://openalex.org/I66760702"]},{"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":"Maharaj Brahma","raw_affiliation_strings":["Natural Language and Information Processing Lab (NLIP ) Indian Institute of Technology Hyderabad Hyderabad , India"],"affiliations":[{"raw_affiliation_string":"Natural Language and Information Processing Lab (NLIP ) Indian Institute of Technology Hyderabad Hyderabad , India","institution_ids":["https://openalex.org/I65181880","https://openalex.org/I55664587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087152480","display_name":"Maunendra Sankar Desarkar","orcid":"https://orcid.org/0000-0003-1963-7338"},"institutions":[{"id":"https://openalex.org/I55664587","display_name":"Indian Institute of Chemical Technology","ror":"https://ror.org/040dky007","country_code":"IN","type":"facility","lineage":["https://openalex.org/I2799351866","https://openalex.org/I4210134808","https://openalex.org/I55664587","https://openalex.org/I66760702"]},{"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":"Maunendra Sankar Desarkar","raw_affiliation_strings":["Natural Language and Information Processing Lab (NLIP ) Indian Institute of Technology Hyderabad Hyderabad , India"],"affiliations":[{"raw_affiliation_string":"Natural Language and Information Processing Lab (NLIP ) Indian Institute of Technology Hyderabad Hyderabad , India","institution_ids":["https://openalex.org/I65181880","https://openalex.org/I55664587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088920217"],"corresponding_institution_ids":["https://openalex.org/I55664587","https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18324984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"33587","last_page":"33614"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.241799995303154,"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":0.241799995303154,"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":0.12690000236034393,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.09049999713897705,"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/context","display_name":"Context (archaeology)","score":0.6728000044822693},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5587999820709229},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.5372999906539917},{"id":"https://openalex.org/keywords/cultural-diversity","display_name":"Cultural diversity","score":0.5074999928474426},{"id":"https://openalex.org/keywords/ethnic-group","display_name":"Ethnic group","score":0.33980000019073486}],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6728000044822693},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5587999820709229},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.5372999906539917},{"id":"https://openalex.org/C125209646","wikidata":"https://www.wikidata.org/wiki/Q1338878","display_name":"Cultural diversity","level":2,"score":0.5074999928474426},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.42829999327659607},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3882000148296356},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.3621000051498413},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3456000089645386},{"id":"https://openalex.org/C137403100","wikidata":"https://www.wikidata.org/wiki/Q41710","display_name":"Ethnic group","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2824999988079071},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.28130000829696655},{"id":"https://openalex.org/C190248442","wikidata":"https://www.wikidata.org/wiki/Q839486","display_name":"Qualitative research","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.26350000500679016},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.2630999982357025},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1706","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1706","pdf_url":"https://aclanthology.org/2025.emnlp-main.1706.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1706","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1706","pdf_url":"https://aclanthology.org/2025.emnlp-main.1706.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035308.pdf","grobid_xml":"https://content.openalex.org/works/W4416035308.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4,17],"widely":[5],"used":[6],"in":[7],"various":[8],"tasks":[9],"and":[10,30,45,52,65,80,97,150,165,181],"applications.However,":[11],"despite":[12],"their":[13],"wide":[14],"capabilities,":[15],"they":[16],"shown":[18],"to":[19,39,58,115],"lack":[20,41,60],"cultural":[21,43,50,117,122,129,135],"alignment":[22,53],"(Ryan":[23],"et":[24,27,35],"al.,":[25,28,36],"2024;AlKhamissi":[26],"2024)":[29,37],"produce":[31],"biased":[32],"generations":[33],"(Naous":[34],"due":[38,57],"a":[40,107,134],"of":[42,47,61,67,75,131],"knowledge":[44],"competence.Evaluation":[46],"LLMs":[48,132],"for":[49,84,111],"awareness":[51],"is":[54,173],"particularly":[55],"challenging":[56],"the":[59,72,78,94,128,141,144],"proper":[62],"evaluation":[63],"metrics":[64],"unavailability":[66],"culturally":[68],"grounded":[69],"datasets":[70,83],"representing":[71],"vast":[73],"complexity":[74],"cultures":[76],"at":[77,93],"regional":[79,95],"sub-regional":[81,163],"levels.Existing":[82],"culture":[85],"specific":[86],"items":[87],"(CSIs)":[88],"focus":[89],"primarily":[90],"on":[91,133],"concepts":[92,123],"level":[96],"may":[98],"contain":[99],"false":[100],"positives.To":[101],"address":[102],"this":[103],"issue,":[104],"we":[105,139,157],"introduce":[106],"novel":[108],"CSI":[109],"dataset":[110,119,172],"Indian":[112],"culture,":[113],"belonging":[114],"17":[116],"facets.The":[118],"comprises":[120],"8k":[121],"from":[124,153],"36":[125],"sub-regions.To":[126],"measure":[127],"competence":[130],"text":[136],"adaptation":[137],"task,":[138],"evaluate":[140],"adaptations":[142,167],"using":[143],"CSIs":[145],"created,":[146],"LLM":[147],"as":[148],"Judge,":[149],"human":[151],"evaluations":[152],"diverse":[154],"socio-demographic":[155],"region.Furthermore,":[156],"perform":[158],"quantitative":[159],"analysis":[160],"demonstrating":[161],"selective":[162],"coverage":[164],"surface-level":[166],"across":[168],"all":[169],"considered":[170],"LLMs.Our":[171],"available":[174],"here:":[175,190],"https://huggingface.co/datasets/nlip/DIWALI,":[176],"project":[177],"webpage":[178],"1":[179],",":[180],"our":[182],"codebase":[183],"with":[184],"model":[185],"outputs":[186],"can":[187],"be":[188],"found":[189],"https://github.com/pramitsahoo/cultureevaluation.":[191]},"counts_by_year":[],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-11-08T00:00:00"}