{"id":"https://openalex.org/W7165645892","doi":"https://doi.org/10.1145/3805689.3806734","title":"Hedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights","display_name":"Hedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights","publication_year":2026,"publication_date":"2026-06-23","ids":{"openalex":"https://openalex.org/W7165645892","doi":"https://doi.org/10.1145/3805689.3806734"},"language":null,"primary_location":{"id":"doi:10.1145/3805689.3806734","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805689.3806734","pdf_url":null,"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 2026 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805689.3806734","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139204956","display_name":"Rafiya Javed","orcid":"https://orcid.org/0000-0002-5911-7188"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rafiya Javed","raw_affiliation_strings":["Google, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5911-7188","affiliations":[{"raw_affiliation_string":"Google, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045494588","display_name":"Cassandra Parent","orcid":"https://orcid.org/0000-0002-0573-3081"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cassandra Parent","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, USA"],"raw_orcid":"https://orcid.org/0000-0002-0573-3081","affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052060244","display_name":"Jackie Kay","orcid":"https://orcid.org/0000-0001-9593-695X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jackie Kay","raw_affiliation_strings":["Independent Researcher, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-9593-695X","affiliations":[{"raw_affiliation_string":"Independent Researcher, London, United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052509590","display_name":"David Yanni","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Yanni","raw_affiliation_strings":["Google, Cambridge, USA"],"raw_orcid":"https://orcid.org/0000-0001-8445-0495","affiliations":[{"raw_affiliation_string":"Google, Cambridge, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139214518","display_name":"Abdullah Zaini","orcid":"https://orcid.org/0009-0005-8770-8435"},"institutions":[{"id":"https://openalex.org/I4210120586","display_name":"Verve Therapeutics (United States)","ror":"https://ror.org/02f7f9m65","country_code":"US","type":"company","lineage":["https://openalex.org/I4210120586"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdullah Zaini","raw_affiliation_strings":["Verily, Cambridge, USA"],"raw_orcid":"https://orcid.org/0009-0005-8770-8435","affiliations":[{"raw_affiliation_string":"Verily, Cambridge, USA","institution_ids":["https://openalex.org/I4210120586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139160346","display_name":"Anushe Sheikh","orcid":"https://orcid.org/0009-0003-6961-3518"},"institutions":[{"id":"https://openalex.org/I117222138","display_name":"Abu Dhabi University","ror":"https://ror.org/01r3kjq03","country_code":"AE","type":"education","lineage":["https://openalex.org/I117222138"]},{"id":"https://openalex.org/I2801277386","display_name":"Emirates Foundation","ror":"https://ror.org/05nd26619","country_code":"AE","type":"other","lineage":["https://openalex.org/I2801277386"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Anushe Sheikh","raw_affiliation_strings":["AI71, Abu Dhabi, United Arab Emirates"],"raw_orcid":"https://orcid.org/0009-0003-6961-3518","affiliations":[{"raw_affiliation_string":"AI71, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I117222138","https://openalex.org/I2801277386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139157098","display_name":"Maribeth Rauh","orcid":"https://orcid.org/0009-0009-9036-4230"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Maribeth Rauh","raw_affiliation_strings":["Trinity College Dublin, AI Accountability Lab, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0009-0009-9036-4230","affiliations":[{"raw_affiliation_string":"Trinity College Dublin, AI Accountability Lab, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065984527","display_name":"Walter Gerych","orcid":"https://orcid.org/0000-0002-1194-1493"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Walter Gerych","raw_affiliation_strings":["Worcester Polytechnic Institute, Worcester, USA"],"raw_orcid":"https://orcid.org/0000-0002-1194-1493","affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, Worcester, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065212897","display_name":"Ramona Comanescu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ramona Comanescu","raw_affiliation_strings":["Google Deepmind, London, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0006-3276-0292","affiliations":[{"raw_affiliation_string":"Google Deepmind, London, United Kingdom","institution_ids":["https://openalex.org/I4210113297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032814084","display_name":"Iason Gabriel","orcid":"https://orcid.org/0000-0002-7552-4576"},"institutions":[{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Iason Gabriel","raw_affiliation_strings":["Google Deepmind, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-7552-4576","affiliations":[{"raw_affiliation_string":"Google Deepmind, London, United Kingdom","institution_ids":["https://openalex.org/I4210113297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070063054","display_name":"Marzyeh Ghassemi","orcid":"https://orcid.org/0000-0001-6349-7251"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marzyeh Ghassemi","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, USA"],"raw_orcid":"https://orcid.org/0000-0001-6349-7251","affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056575786","display_name":"Laura Weidinger","orcid":"https://orcid.org/0000-0002-5189-760X"},"institutions":[{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Laura Weidinger","raw_affiliation_strings":["Google Deepmind, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-5189-760X","affiliations":[{"raw_affiliation_string":"Google Deepmind, London, United Kingdom","institution_ids":["https://openalex.org/I4210113297"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2025","last_page":"2054"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14013","display_name":"Legal Language and Interpretation","score":0.08569999784231186,"subfield":{"id":"https://openalex.org/subfields/3308","display_name":"Law"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T14013","display_name":"Legal Language and Interpretation","score":0.08569999784231186,"subfield":{"id":"https://openalex.org/subfields/3308","display_name":"Law"},"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/T14012","display_name":"Comparative and International Law Studies","score":0.03909999877214432,"subfield":{"id":"https://openalex.org/subfields/3308","display_name":"Law"},"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/T14288","display_name":"Law, Rights, and Freedoms","score":0.03669999912381172,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/human-rights","display_name":"Human rights","score":0.47530001401901245},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.2590000033378601},{"id":"https://openalex.org/keywords/government","display_name":"Government (linguistics)","score":0.25859999656677246},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.25679999589920044},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.25519999861717224}],"concepts":[{"id":"https://openalex.org/C169437150","wikidata":"https://www.wikidata.org/wiki/Q8458","display_name":"Human rights","level":2,"score":0.47530001401901245},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.430400013923645},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.4244000017642975},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.4050999879837036},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.38260000944137573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3440999984741211},{"id":"https://openalex.org/C190253527","wikidata":"https://www.wikidata.org/wiki/Q295354","display_name":"Law and economics","level":1,"score":0.2883000075817108},{"id":"https://openalex.org/C100001284","wikidata":"https://www.wikidata.org/wiki/Q2248246","display_name":"Public economics","level":1,"score":0.2757999897003174},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805689.3806734","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805689.3806734","pdf_url":null,"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 2026 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805689.3806734","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805689.3806734","pdf_url":null,"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 2026 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W33891176","https://openalex.org/W2069069726","https://openalex.org/W2124444413","https://openalex.org/W2605384053","https://openalex.org/W2750285009","https://openalex.org/W2997588435","https://openalex.org/W3022840527","https://openalex.org/W3096290781","https://openalex.org/W3123340107","https://openalex.org/W3133774865","https://openalex.org/W3160638507","https://openalex.org/W4249470828","https://openalex.org/W4393160939","https://openalex.org/W4399426804","https://openalex.org/W4402670310","https://openalex.org/W4414037010","https://openalex.org/W4416853758","https://openalex.org/W7133241667"],"related_works":[],"abstract_inverted_index":{"Hedging":[0],"and":[1,78,82,93,165,178,195],"non-affirmation":[2,94,179],"are":[3,22,28,126],"behaviors":[4,21,51],"exhibited":[5],"by":[6],"large":[7,63],"language":[8],"models":[9,65,159],"(LLMs)":[10],"that":[11,84,95,183],"limit":[12],"the":[13,31,85,100,103,130,144,150,174,187],"clear":[14],"endorsement":[15],"of":[16,33,89,102,132,142,153,176],"specific":[17],"statements.":[18],"While":[19,105],"these":[20,50,154,169],"desirable":[23],"in":[24,30,52],"subjective":[25],"contexts,":[26],"they":[27],"undesirable":[29],"context":[32],"human":[34],"rights":[35],"-":[36],"which":[37],"apply":[38],"unambiguously":[39],"to":[40,48,140,160,168,198],"all":[41],"groups.":[42,59],"We":[43,60,181],"present":[44],"a":[45],"systematic":[46,136],"framework":[47],"measure":[49],"unconstrained":[53],"LLM":[54,71],"responses":[55],"regarding":[56],"various":[57],"identity":[58,101,112,133,148],"evaluate":[61],"six":[62],"proprietary":[64],"as":[66,68],"well":[67],"one":[69],"open-weight":[70,158],"on":[72,99],"4738":[73],"prompts":[74],"across":[75,192],"205":[76],"national":[77],"stateless":[79],"ethnic":[80],"identities":[81,171],"find":[83,182],"majority":[86],"(4":[87],"out":[88],"7)":[90],"display":[91],"hedging":[92,177],"is":[96,113,138,149,186,196],"significantly":[97],"dependent":[98],"group.":[104],"factors":[106],"like":[107],"conflict":[108],"signals,":[109],"sovereignty":[110],"(whether":[111],"stateless),":[114],"or":[115],"economic":[116],"indicators":[117],"(GDP)":[118],"also":[119],"influence":[120],"model":[121],"behavior,":[122],"their":[123],"effect":[124],"sizes":[125],"consistently":[127],"weaker":[128],"than":[129],"impact":[131],"itself.":[134],"The":[135],"disparity":[137],"robust":[139,197],"methods":[141],"rephrasing":[143],"prompts.":[145],"Since":[146],"group":[147,170,184],"strongest":[151],"predictor":[152],"behaviors,":[155],"we":[156],"use":[157],"explore":[161],"whether":[162],"applying":[163],"steering":[164,185],"orthogonalization":[166],"techniques":[167],"can":[172],"mitigate":[173],"rates":[175],"behaviors.":[180],"most":[188],"effective":[189],"debiasing":[190],"approach":[191],"query":[193],"types":[194],"downstream":[199],"forgetting.":[200]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-06-24T00:00:00"}
