{"id":"https://openalex.org/W4414360383","doi":"https://doi.org/10.24963/ijcai.2025/1141","title":"Reflective Verbal Reward Design for Pluralistic Alignment","display_name":"Reflective Verbal Reward Design for Pluralistic Alignment","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360383","doi":"https://doi.org/10.24963/ijcai.2025/1141"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/1141","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5089789107","display_name":"Carter Blair","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Carter Blair","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105978897","display_name":"Kate Larson","orcid":"https://orcid.org/0000-0002-5455-9657"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kate Larson","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058482884","display_name":"Edith Law","orcid":"https://orcid.org/0000-0002-7540-075X"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Edith Law","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5089789107"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26819476,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10271","last_page":"10279"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13836","display_name":"Educational Research and Pedagogy","score":0.4361000061035156,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T13836","display_name":"Educational Research and Pedagogy","score":0.4361000061035156,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T13932","display_name":"Education, Technology, and Economics","score":0.3804999887943268,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13970","display_name":"Pharmacy and Medical Practices","score":0.3603000044822693,"subfield":{"id":"https://openalex.org/subfields/3004","display_name":"Pharmacology"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6186000108718872},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5602999925613403},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5458999872207642},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4652999937534332},{"id":"https://openalex.org/keywords/corrective-feedback","display_name":"Corrective feedback","score":0.43560001254081726},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.39399999380111694},{"id":"https://openalex.org/keywords/reward-system","display_name":"Reward system","score":0.3582000136375427}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6186000108718872},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5709999799728394},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5602999925613403},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.5472999811172485},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5458999872207642},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4936000108718872},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4652999937534332},{"id":"https://openalex.org/C2779305910","wikidata":"https://www.wikidata.org/wiki/Q5172809","display_name":"Corrective feedback","level":2,"score":0.43560001254081726},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.39399999380111694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38359999656677246},{"id":"https://openalex.org/C143661069","wikidata":"https://www.wikidata.org/wiki/Q670713","display_name":"Reward system","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C117035363","wikidata":"https://www.wikidata.org/wiki/Q3769299","display_name":"Human behavior","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.310699999332428},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.28600001335144043},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.28040000796318054},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26100000739097595},{"id":"https://openalex.org/C145633318","wikidata":"https://www.wikidata.org/wiki/Q207125","display_name":"Nonverbal communication","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2025/1141","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:share.osf.io:9e03fa6c-4fed-450f-89e2-49e808334493","is_oa":false,"landing_page_url":"https://osf.io/8yxf2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401127","display_name":"OSF Preprints (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"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":"Project"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"AI":[0],"agents":[1],"are":[2,36],"commonly":[3],"aligned":[4],"with":[5,134],"\"human":[6],"values\"":[7],"through":[8,82],"reinforcement":[9],"learning":[10,69,158],"from":[11,22],"human":[12,24,34],"feedback":[13,25,47],"(RLHF),":[14],"where":[15,85],"a":[16,49,63,76,124,140],"single":[17,50],"reward":[18,51,65,71,119,126,148],"model":[19,52,78,113],"is":[20,105],"learned":[21],"aggregated":[23],"and":[26,42,90,102],"used":[27,107],"to":[28,79],"align":[29],"an":[30,117],"agent's":[31],"behavior.":[32],"However,":[33],"values":[35],"not":[37],"homogeneous--different":[38],"people":[39],"hold":[40],"distinct":[41],"sometimes":[43],"conflicting":[44],"values.":[45],"Aggregating":[46],"into":[48],"risks":[53],"disproportionately":[54],"suppressing":[55],"minority":[56],"preferences.":[57,93],"To":[58],"address":[59],"this,":[60],"we":[61,122],"present":[62],"novel":[64],"modeling":[66],"approach":[67,74],"for":[68,110,128],"individualized":[70,118],"models.":[72],"Our":[73],"uses":[75],"language":[77,112],"guide":[80],"users":[81],"reflective":[83],"dialogues":[84],"they":[86],"critique":[87],"agent":[88],"behavior":[89],"construct":[91],"their":[92],"This":[94],"personalized":[95],"dialogue":[96],"history,":[97],"containing":[98],"the":[99],"user's":[100],"reflections":[101],"critiqued":[103],"examples,":[104],"then":[106],"as":[108,116],"context":[109],"another":[111],"that":[114],"serves":[115],"function":[120],"(what":[121],"call":[123],"\"verbal":[125],"model\")":[127],"evaluating":[129],"new":[130],"trajectories.":[131],"In":[132],"studies":[133],"30":[135],"participants,":[136],"our":[137],"method":[138],"achieved":[139],"9-12%":[141],"improvement":[142],"in":[143],"accuracy":[144],"over":[145],"non-reflective":[146],"verbal":[147],"models":[149],"while":[150],"being":[151],"more":[152],"sample":[153],"efficient":[154],"than":[155],"traditional":[156],"supervised":[157],"methods.":[159]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}