{"id":"https://openalex.org/W7167932541","doi":"https://doi.org/10.1145/3805712.3809689","title":"One Adapts to Any: Meta Reward Modeling for Personalized LLM Alignment","display_name":"One Adapts to Any: Meta Reward Modeling for Personalized LLM Alignment","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167932541","doi":"https://doi.org/10.1145/3805712.3809689"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809689","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809689","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809689","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043285342","display_name":"Hongru Cai","orcid":"https://orcid.org/0009-0007-9857-6639"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hongru Cai","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0007-9857-6639","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101599249","display_name":"Yongqi Li","orcid":"https://orcid.org/0000-0002-6932-4228"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yongqi Li","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-6932-4228","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081246075","display_name":"Tiezheng Yu","orcid":"https://orcid.org/0000-0001-5396-950X"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Tiezheng Yu","raw_affiliation_strings":["Huawei Technologies Ltd., Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-5396-950X","affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd., Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029052244","display_name":"Fengbin Zhu","orcid":"https://orcid.org/0000-0001-6776-2040"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Fengbin Zhu","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6776-2040","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368524","display_name":"Wenjie Wang","orcid":"https://orcid.org/0000-0002-5199-1428"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjie Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-5199-1428","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051925942","display_name":"Fuli Feng","orcid":"https://orcid.org/0000-0002-5828-9842"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuli Feng","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-5828-9842","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100408983","display_name":"Wenjie Li","orcid":"https://orcid.org/0000-0002-7360-8864"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wenjie Li","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-7360-8864","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.95093808,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"110","last_page":"121"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.7961999773979187,"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"}},"topics":[{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.7961999773979187,"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/T10028","display_name":"Topic Modeling","score":0.02889999933540821,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.01720000058412552,"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/personalization","display_name":"Personalization","score":0.6916000247001648},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6218000054359436},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5735999941825867},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3765999972820282},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.37299999594688416},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3709000051021576},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.36629998683929443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8425999879837036},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.6916000247001648},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6218000054359436},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5735999941825867},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4986000061035156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49790000915527344},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3765999972820282},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C67712803","wikidata":"https://www.wikidata.org/wiki/Q7901853","display_name":"User modeling","level":3,"score":0.3183000087738037},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30140000581741333},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2678000032901764},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809689","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809689","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809689","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809689","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2535690855","https://openalex.org/W2763110165","https://openalex.org/W2963825865","https://openalex.org/W2964983698","https://openalex.org/W4322760294","https://openalex.org/W4384659101","https://openalex.org/W4385572014","https://openalex.org/W4404781903","https://openalex.org/W7125014624","https://openalex.org/W7133211372","https://openalex.org/W7133239970"],"related_works":[],"abstract_inverted_index":{"Alignment":[0],"of":[1,47,110,118],"Large":[2],"Language":[3],"Models":[4],"(LLMs)":[5],"aims":[6],"to":[7,19,58,76,78,127],"align":[8],"outputs":[9],"with":[10],"human":[11],"preferences,":[12],"and":[13,32,52,114,169],"personalized":[14,25,92,157],"alignment":[15],"further":[16],"adapts":[17],"models":[18,27,40,75],"individual":[20,50],"users.":[21,60],"This":[22],"relies":[23],"on":[24,148,156],"reward":[26,93,104,112],"that":[28,63,161],"capture":[29],"user-specific":[30],"preferences":[31],"automatically":[33],"provide":[34],"individualized":[35],"feedback.":[36,133],"However,":[37],"developing":[38],"these":[39,65,119],"faces":[41],"two":[42],"critical":[43],"challenges:":[44],"the":[45,53,116,139],"scarcity":[46],"feedback":[48],"from":[49,71],"users":[51,150],"need":[54],"for":[55],"efficient":[56],"adaptation":[57,130],"unseen":[59],"We":[61,173],"argue":[62],"addressing":[64],"constraints":[66],"requires":[67],"a":[68,96,107,122],"paradigm":[69],"shift":[70],"fitting":[72],"static":[73],"user":[74,167],"''learning":[77],"learn''":[79],"adaptation.":[80],"To":[81,134],"realize":[82],"this,":[83],"we":[84,100,137],"propose":[85],"Meta":[86],"Reward":[87],"Modeling":[88],"(MRM),":[89],"which":[90,144],"reformulates":[91],"modeling":[94],"as":[95,106],"meta-learning":[97],"problem.":[98],"Specifically,":[99],"represent":[101],"each":[102],"user's":[103],"model":[105],"weighted":[108],"combination":[109],"base":[111],"functions,":[113],"optimize":[115],"initialization":[117],"weights":[120],"using":[121],"Model-Agnostic":[123],"Meta-Learning":[124],"(MAML)-style":[125],"framework":[126],"support":[128],"fast":[129],"under":[131],"limited":[132],"ensure":[135],"robustness,":[136,168],"introduce":[138],"Robust":[140],"Personalization":[141],"Objective":[142],"(RPO),":[143],"places":[145],"greater":[146],"emphasis":[147],"hard-to-learn":[149],"during":[151],"meta":[152],"optimization.":[153],"Extensive":[154],"experiments":[155],"preference":[158],"datasets":[159],"validate":[160],"MRM":[162],"enhances":[163],"few-shot":[164],"personalization,":[165],"improves":[166],"consistently":[170],"outperforms":[171],"baselines.":[172],"release":[174],"code":[175],"at":[176],"https://github.com/ModalityDance/MRM.":[177]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-11T00:00:00"}