{"id":"https://openalex.org/W4392828339","doi":"https://doi.org/10.48550/arxiv.2403.08743","title":"Prompting Fairness: Integrating Causality to Debias Large Language Models","display_name":"Prompting Fairness: Integrating Causality to Debias Large Language Models","publication_year":2024,"publication_date":"2024-03-13","ids":{"openalex":"https://openalex.org/W4392828339","doi":"https://doi.org/10.48550/arxiv.2403.08743"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2403.08743","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.08743","pdf_url":"https://arxiv.org/pdf/2403.08743","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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/2403.08743","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112598840","display_name":"Jingling Li","orcid":"https://orcid.org/0009-0007-2769-2851","observed_orcids":["https://orcid.org/0009-0007-2769-2851"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jingling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006403327","display_name":"Zeyu Tang","orcid":"https://orcid.org/0000-0002-4423-4728","observed_orcids":["https://orcid.org/0000-0002-4423-4728"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tang, Zeyu","raw_affiliation_strings":["Department of Philosophy , Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Philosophy , Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087260621","display_name":"Xiaoyu Liu","orcid":"https://orcid.org/0000-0002-1519-494X","observed_orcids":["https://orcid.org/0000-0002-1519-494X"]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Xiaoyu","raw_affiliation_strings":["Department of Computer Science , University of Maryland , College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Maryland , College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047533473","display_name":"Peter Spirtes","orcid":"https://orcid.org/0000-0002-1385-190X","observed_orcids":["https://orcid.org/0000-0002-1385-190X"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Spirtes, Peter","raw_affiliation_strings":["Department of Philosophy , Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Philosophy , Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342309","display_name":"Kun Zhang","orcid":"https://orcid.org/0000-0002-0738-9958","observed_orcids":["https://orcid.org/0000-0002-0738-9958"]},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["AE","US"],"is_corresponding":false,"raw_author_name":"Zhang, Kun","raw_affiliation_strings":["Department of Philosophy , Carnegie Mellon University","Machine Learning Department , Mohamed bin Zayed University of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Philosophy , Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Machine Learning Department , Mohamed bin Zayed University of Artificial Intelligence","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011342505","display_name":"Liu Leqi","orcid":"https://orcid.org/0000-0002-9707-4529","observed_orcids":["https://orcid.org/0000-0002-9707-4529"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leqi, Liu","raw_affiliation_strings":["University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113055770","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0001-9253-5763","observed_orcids":["https://orcid.org/0000-0001-9253-5763"]},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Yang","raw_affiliation_strings":["Computer Science and Engineering Department , University of California , Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department , University of California , Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":37,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.989300012588501,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.989300012588501,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.004000000189989805,"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/T10028","display_name":"Topic Modeling","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/large-language-models","display_name":"large language models","score":0.8899999856948853},{"id":"https://openalex.org/keywords/bias-mitigation","display_name":"bias mitigation","score":0.9330000281333923},{"id":"https://openalex.org/keywords/social-bias","display_name":"social bias","score":0.7429999709129333},{"id":"https://openalex.org/keywords/prompting-strategies","display_name":"prompting strategies","score":0.8880000114440918},{"id":"https://openalex.org/keywords/social-information","display_name":"social information","score":0.42500001192092896},{"id":"https://openalex.org/keywords/causal-pathways","display_name":"causal pathways","score":0.7630000114440918},{"id":"https://openalex.org/keywords/black-box-access","display_name":"black-box access","score":0.6420000195503235},{"id":"https://openalex.org/keywords/algorithmic-fairness","display_name":"algorithmic fairness","score":0.6480000019073486}],"concepts":[{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.9779196381568909},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.6032392978668213},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3628484010696411},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.35678231716156006},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.2451593279838562},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11050701141357422},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2403.08743","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.08743","pdf_url":"https://arxiv.org/pdf/2403.08743","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2403.08743","doi":"https://doi.org/10.48550/arxiv.2403.08743","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.08743","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":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.08743","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.08743","pdf_url":"https://arxiv.org/pdf/2403.08743","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7578999996185303,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G2521135176","display_name":"Interpretable graphical models for large multi-modal COPD data (R01HL159805)","funder_award_id":"R01HL159805","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"},{"id":"https://openalex.org/G826810440","display_name":"AI Institute for Societal Decision Making (AI-SDM)","funder_award_id":"2229881","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337338","display_name":"National Heart, Lung, and Blood Institute","ror":"https://ror.org/012pb6c26"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392828339.pdf","grobid_xml":"https://content.openalex.org/works/W4392828339.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W2545995787","https://openalex.org/W2942370121","https://openalex.org/W2963381846","https://openalex.org/W2972020530","https://openalex.org/W3155655882","https://openalex.org/W3197748091","https://openalex.org/W3204096139","https://openalex.org/W3207316473","https://openalex.org/W4306808680","https://openalex.org/W4307123883","https://openalex.org/W4321162379","https://openalex.org/W4327810158","https://openalex.org/W4365460762","https://openalex.org/W4367692219","https://openalex.org/W4380356267","https://openalex.org/W4385571830","https://openalex.org/W4385774833","https://openalex.org/W4387560733","https://openalex.org/W4389471473","https://openalex.org/W4389518789","https://openalex.org/W4390041933","https://openalex.org/W4404783679","https://openalex.org/W4409362346","https://openalex.org/W4412945536","https://openalex.org/W4415796002","https://openalex.org/W7126411810","https://openalex.org/W7133235460"],"related_works":["https://openalex.org/W7160745628","https://openalex.org/W4409362346","https://openalex.org/W4416034202","https://openalex.org/W4404518541","https://openalex.org/W7126183608","https://openalex.org/W7127987255","https://openalex.org/W4414792190","https://openalex.org/W7213432600","https://openalex.org/W4409362698","https://openalex.org/W7124294891"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs),":[3],"despite":[4],"their":[5],"remarkable":[6],"capabilities,":[7],"are":[8],"susceptible":[9],"to":[10,40,45,66,118,153],"generating":[11],"biased":[12,125],"and":[13,24,53],"discriminatory":[14],"responses.":[15],"As":[16],"LLMs":[17],"increasingly":[18],"influence":[19],"high-stakes":[20],"decision-making":[21],"(e.g.,":[22],"hiring":[23],"healthcare),":[25],"mitigating":[26],"these":[27,81,91],"biases":[28],"becomes":[29],"critical.":[30],"In":[31],"this":[32],"work,":[33],"we":[34,84],"propose":[35],"a":[36,63],"causality-guided":[37],"debiasing":[38,103,145],"framework":[39,61,97,131],"tackle":[41],"social":[42,55,69,126],"biases,":[43],"aiming":[44],"reduce":[46],"the":[47,54,58,116,154],"objectionable":[48],"dependence":[49],"between":[50],"LLMs'":[51],"decisions":[52],"information":[56,70],"in":[57,144],"input.":[59],"Our":[60],"introduces":[62],"novel":[64],"perspective":[65],"identify":[67],"how":[68],"can":[71],"affect":[72],"an":[73],"LLM's":[74],"decision":[75],"through":[76,93,132],"different":[77],"causal":[78,82],"pathways.":[79],"Leveraging":[80],"insights,":[83],"outline":[85],"principled":[86],"prompting":[87],"strategies":[88],"that":[89],"regulate":[90],"pathways":[92],"selection":[94],"mechanisms.":[95],"This":[96],"not":[98],"only":[99,150],"unifies":[100],"existing":[101],"prompting-based":[102],"techniques,":[104],"but":[105],"also":[106],"opens":[107],"up":[108],"new":[109],"directions":[110],"for":[111],"reducing":[112],"bias":[113],"by":[114],"encouraging":[115],"model":[117],"prioritize":[119],"fact-based":[120],"reasoning":[121],"over":[122],"reliance":[123],"on":[124,135],"cues.":[127],"We":[128],"validate":[129],"our":[130],"extensive":[133],"experiments":[134],"real-world":[136],"datasets":[137],"across":[138],"multiple":[139],"domains,":[140],"demonstrating":[141],"its":[142],"effectiveness":[143],"LLM":[146],"decisions,":[147],"even":[148],"with":[149],"black-box":[151],"access":[152],"model.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":9}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2024-03-15T00:00:00"}