{"id":"https://openalex.org/W4401381452","doi":"https://doi.org/10.1145/3677525.3678666","title":"Indian-BhED: A Dataset for Measuring India-Centric Biases in Large Language Models","display_name":"Indian-BhED: A Dataset for Measuring India-Centric Biases in Large Language Models","publication_year":2024,"publication_date":"2024-08-07","ids":{"openalex":"https://openalex.org/W4401381452","doi":"https://doi.org/10.1145/3677525.3678666"},"language":"en","primary_location":{"id":"doi:10.1145/3677525.3678666","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3677525.3678666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Information Technology for Social Good","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106343254","display_name":"Khyati Khandelwal","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4210156248","display_name":"Oxford Institute for Energy Studies","ror":"https://ror.org/04f1srs73","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210156248"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Khyati Khandelwal","raw_affiliation_strings":["University of Oxford, United Kingdom","Oxford Internet Institute, University of Oxford, UK","Oxford Internet Institute, Uni-versity of Oxford, Oxford, UK"],"raw_orcid":"https://orcid.org/0009-0000-8889-2901","affiliations":[{"raw_affiliation_string":"University of Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Oxford Internet Institute, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Oxford Internet Institute, Uni-versity of Oxford, Oxford, UK","institution_ids":["https://openalex.org/I4210156248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003730904","display_name":"Manuel Tonneau","orcid":"https://orcid.org/0009-0008-4954-3133"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Manuel Tonneau","raw_affiliation_strings":["University of Oxford, United Kingdom","Oxford Internet Institute, University of Oxford, UK"],"raw_orcid":"https://orcid.org/0009-0008-4954-3133","affiliations":[{"raw_affiliation_string":"University of Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Oxford Internet Institute, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001652638","display_name":"Andrew M. Bean","orcid":"https://orcid.org/0000-0001-8439-5975"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew M. Bean","raw_affiliation_strings":["University of Oxford, United Kingdom","Oxford Internet Institute, University of Oxford, UK"],"raw_orcid":"https://orcid.org/0000-0001-8439-5975","affiliations":[{"raw_affiliation_string":"University of Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Oxford Internet Institute, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051050719","display_name":"Hannah Rose Kirk","orcid":"https://orcid.org/0000-0002-7419-5993"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hannah Rose Kirk","raw_affiliation_strings":["University of Oxford, United Kingdom","Oxford Internet Institute, University of Oxford, UK"],"raw_orcid":"https://orcid.org/0000-0002-7419-5993","affiliations":[{"raw_affiliation_string":"University of Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Oxford Internet Institute, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029882049","display_name":"Scott A. Hale","orcid":"https://orcid.org/0000-0002-6894-4951"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Scott A. Hale","raw_affiliation_strings":["University of Oxford, United Kingdom","Oxford Internet Institute, University of Oxford, UK"],"raw_orcid":"https://orcid.org/0000-0002-6894-4951","affiliations":[{"raw_affiliation_string":"University of Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Oxford Internet Institute, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.8874,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.9422123,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"231","last_page":"239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8892999887466431,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.8892999887466431,"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/T13718","display_name":"Media Influence and Politics","score":0.8871999979019165,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.8629000186920166,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6008366942405701},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3856053352355957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32108402252197266}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6008366942405701},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3856053352355957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32108402252197266}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3677525.3678666","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3677525.3678666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Information Technology for Social Good","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2143207134","display_name":null,"funder_award_id":"ES/X502352/1","funder_id":"https://openalex.org/F4320334630","funder_display_name":"Economic and Social Research Council"}],"funders":[{"id":"https://openalex.org/F4320334630","display_name":"Economic and Social Research Council","ror":"https://ror.org/03n0ht308"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2019775665","https://openalex.org/W2027941666","https://openalex.org/W2075121699","https://openalex.org/W2108933576","https://openalex.org/W2160742149","https://openalex.org/W2166504966","https://openalex.org/W2235036793","https://openalex.org/W2797847923","https://openalex.org/W2917240770","https://openalex.org/W2950888501","https://openalex.org/W2962833164","https://openalex.org/W2997450457","https://openalex.org/W3015520400","https://openalex.org/W3035390927","https://openalex.org/W3135514117","https://openalex.org/W3138223498","https://openalex.org/W3155091141","https://openalex.org/W3202145518","https://openalex.org/W4229596818","https://openalex.org/W4285199616","https://openalex.org/W4385574250","https://openalex.org/W4390227104","https://openalex.org/W6876097961"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs),":[3],"now":[4],"used":[5],"daily":[6],"by":[7],"millions,":[8],"can":[9],"encode":[10],"societal":[11],"biases,":[12],"exposing":[13],"their":[14],"users":[15],"to":[16,39,60,99,109,173],"representational":[17],"harms.":[18],"A":[19],"large":[20],"body":[21],"of":[22,68,80,92,111,146,152,182],"scholarship":[23],"on":[24],"LLM":[25],"bias":[26,40,55,112],"exists":[27],"but":[28],"it":[29],"predominantly":[30],"adopts":[31],"a":[32,66,96,135,144],"Western-centric":[33],"frame":[34,63],"and":[35,42,74,82,122,131,155,169,177,198],"attends":[36],"comparatively":[37],"less":[38],"levels":[41],"potential":[43,161],"harms":[44],"in":[45,56,77,85,102,115,167,196],"the":[46,78,90,103,116,150,186],"Global":[47],"South.":[48],"In":[49],"this":[50,183],"paper,":[51],"we":[52,125],"quantify":[53],"stereotypical":[54,73,141,176],"popular":[57],"LLMs":[58,93],"according":[59],"an":[61],"Indian-centric":[62],"through":[64],"Indian-BhED,":[65],"first":[67],"its":[69],"kind":[70],"dataset,":[71],"containing":[72],"anti-stereotypical":[75,178],"examples":[76],"context":[79],"caste":[81,153],"religious":[83],"stereotypes":[84,101],"India.":[86],"We":[87,158],"find":[88,126],"that":[89,127],"majority":[91],"tested":[94],"have":[95,134],"strong":[97],"propensity":[98,138],"output":[100],"Indian":[104],"context,":[105,118],"especially":[106],"when":[107,193],"compared":[108],"axes":[110,151],"traditionally":[113],"studied":[114],"Western":[117],"such":[119,164],"as":[120,143],"gender":[121],"race.":[123],"Notably,":[124],"GPT-2,":[128],"GPT-2":[129],"Large,":[130],"GPT":[132],"3.5":[133],"particularly":[136],"high":[137],"for":[139,149,163,188],"preferring":[140],"outputs":[142],"percent":[145],"all":[147],"sentences":[148],"(63\u201379%)":[154],"religion":[156],"(69\u201372%).":[157],"finally":[159],"investigate":[160],"causes":[162],"harmful":[165],"behaviour":[166],"LLMs,":[168],"posit":[170],"intervention":[171],"techniques":[172],"reduce":[174],"both":[175],"biases.":[179],"The":[180],"findings":[181],"work":[184],"highlight":[185],"need":[187],"including":[189],"more":[190],"diverse":[191],"voices":[192],"researching":[194],"fairness":[195],"AI":[197],"evaluating":[199],"LLMs.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":8}],"updated_date":"2026-06-25T08:15:23.626066","created_date":"2025-10-10T00:00:00"}