{"id":"https://openalex.org/W4417530723","doi":"https://doi.org/10.1145/3773966.3779376","title":"From Personalization to Prejudice: Bias and Discrimination in Memory-Enhanced AI Agents for Recruitment","display_name":"From Personalization to Prejudice: Bias and Discrimination in Memory-Enhanced AI Agents for Recruitment","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W4417530723","doi":"https://doi.org/10.1145/3773966.3779376"},"language":null,"primary_location":{"id":"doi:10.1145/3773966.3779376","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3779376","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3773966.3779376","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Himanshu Gharat","orcid":"https://orcid.org/0009-0009-9292-2662"},"institutions":[{"id":"https://openalex.org/I2800685081","display_name":"Tata Chemicals (India)","ror":"https://ror.org/03b6pnq25","country_code":"IN","type":"company","lineage":["https://openalex.org/I2800685081","https://openalex.org/I4210086519"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Himanshu Gharat","raw_affiliation_strings":["Phi Labs, Quantiphi Inc., Mumbai, Maharashtra, India"],"raw_orcid":"https://orcid.org/0009-0009-9292-2662","affiliations":[{"raw_affiliation_string":"Phi Labs, Quantiphi Inc., Mumbai, Maharashtra, India","institution_ids":["https://openalex.org/I2800685081"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Himanshi Agrawal","orcid":"https://orcid.org/0009-0005-6448-300X"},"institutions":[{"id":"https://openalex.org/I4210102658","display_name":"Sami Labs (India)","ror":"https://ror.org/01cryga93","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210102658"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Himanshi Agrawal","raw_affiliation_strings":["Phi Labs, Quantiphi Inc., Bengaluru, Karnataka, India"],"raw_orcid":"https://orcid.org/0009-0005-6448-300X","affiliations":[{"raw_affiliation_string":"Phi Labs, Quantiphi Inc., Bengaluru, Karnataka, India","institution_ids":["https://openalex.org/I4210102658"]}]},{"author_position":"last","author":{"id":null,"display_name":"Gourab K. Patro","orcid":"https://orcid.org/0000-0002-2435-6859"},"institutions":[{"id":"https://openalex.org/I4210102658","display_name":"Sami Labs (India)","ror":"https://ror.org/01cryga93","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210102658"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Gourab K. Patro","raw_affiliation_strings":["Phi Labs, Quantiphi Inc., Bengaluru, Karnataka, India"],"raw_orcid":"https://orcid.org/0000-0002-2435-6859","affiliations":[{"raw_affiliation_string":"Phi Labs, Quantiphi Inc., Bengaluru, Karnataka, India","institution_ids":["https://openalex.org/I4210102658"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2800685081"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01325706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1140","last_page":"1144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.21729999780654907,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.21729999780654907,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.17180000245571136,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.1331000030040741,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"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/personalization","display_name":"Personalization","score":0.8432999849319458},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6736999750137329},{"id":"https://openalex.org/keywords/gender-bias","display_name":"Gender bias","score":0.27059999108314514},{"id":"https://openalex.org/keywords/cognitive-bias","display_name":"Cognitive bias","score":0.26649999618530273}],"concepts":[{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.8432999849319458},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6736999750137329},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5468000173568726},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.43790000677108765},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3709999918937683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3447999954223633},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3312000036239624},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.2833999991416931},{"id":"https://openalex.org/C2983427547","wikidata":"https://www.wikidata.org/wiki/Q93200","display_name":"Gender bias","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C189216375","wikidata":"https://www.wikidata.org/wiki/Q1127759","display_name":"Cognitive bias","level":3,"score":0.26649999618530273},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2524000108242035}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3773966.3779376","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3779376","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.16532","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.16532","pdf_url":"https://arxiv.org/pdf/2512.16532","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3773966.3779376","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3779376","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4,67],"empowered":[5],"AI":[6,146],"agents":[7,79,119],"with":[8],"advanced":[9],"capabilities":[10],"for":[11,136],"understanding,":[12],"reasoning,":[13],"and":[14,35,41,72,99,102,107,110,129],"interacting":[15],"across":[16,29,111],"diverse":[17],"tasks.":[18],"The":[19],"addition":[20],"of":[21,39,61,94,114],"memory":[22,53],"further":[23],"enhances":[24],"them":[25],"by":[26],"enabling":[27],"continuity":[28],"interactions,":[30],"learning":[31],"from":[32],"past":[33],"experiences,":[34],"improving":[36],"the":[37,92,134],"relevance":[38],"actions":[40],"responses":[42],"over":[43],"time;":[44],"termed":[45],"as":[46,85],"memory-enhanced":[47,77,96,144],"personalization.":[48],"Although":[49],"such":[50],"personalization":[51],"through":[52,131],"offers":[54],"clear":[55],"benefits,":[56],"it":[57],"also":[58],"introduces":[59],"risks":[60],"bias.":[62],"While":[63],"several":[64],"previous":[65],"studies":[66],"highlighted":[68],"bias":[69,74,104,125],"in":[70,109,143],"ML":[71],"LLMs,":[73],"due":[75],"to":[76],"personalized":[78,97],"is":[80,105,126],"largely":[81],"unexplored.":[82],"Using":[83],"recruitment":[84],"an":[86],"example":[87],"use":[88],"case,":[89],"we":[90],"simulate":[91],"behavior":[93],"a":[95],"agent,":[98],"study":[100],"whether":[101],"how":[103],"introduced":[106,128],"amplified":[108],"various":[112],"stages":[113],"operation.":[115],"Our":[116],"experiments":[117],"on":[118],"using":[120],"safety-trained":[121],"LLMs":[122],"reveal":[123],"that":[124],"systematically":[127],"reinforced":[130],"personalization,":[132],"emphasizing":[133],"need":[135],"additional":[137],"protective":[138],"measures":[139],"or":[140],"agent":[141],"guardrails":[142],"LLM-based":[145],"agents.":[147]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-21T00:00:00"}