{"id":"https://openalex.org/W7164572813","doi":"https://doi.org/10.1109/msp.2026.3666824","title":"Aligning Large Language Models With Human Feedback: Mathematical foundations and algorithm design [Special Issue on the Mathematics of Deep Learning]","display_name":"Aligning Large Language Models With Human Feedback: Mathematical foundations and algorithm design [Special Issue on the Mathematics of Deep Learning]","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7164572813","doi":"https://doi.org/10.1109/msp.2026.3666824"},"language":null,"primary_location":{"id":"doi:10.1109/msp.2026.3666824","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2026.3666824","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-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/A5111331875","display_name":"Siliang Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I872623138","display_name":"Search for Extraterrestrial Intelligence","ror":"https://ror.org/02dxgk712","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I872623138"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siliang Zeng","raw_affiliation_strings":["ByteDance Seed, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed, Mountain View, CA, USA","institution_ids":["https://openalex.org/I872623138"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083025579","display_name":"Luca Viano","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Luca Viano","raw_affiliation_strings":["École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland"],"raw_orcid":"https://orcid.org/0009-0002-1028-6893","affiliations":[{"raw_affiliation_string":"École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138491572","display_name":"Chenliang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenliang Li","raw_affiliation_strings":["Texas A&M University, College Station, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138505378","display_name":"Jiaxiang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaxiang Li","raw_affiliation_strings":["Meta, Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta, Santa Clara, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002747297","display_name":"Markus Wulfmeier","orcid":"https://orcid.org/0000-0003-1802-4492"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"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":"Markus Wulfmeier","raw_affiliation_strings":["Google DeepMind, London, U.K"],"raw_orcid":"https://orcid.org/0000-0003-1802-4492","affiliations":[{"raw_affiliation_string":"Google DeepMind, London, U.K","institution_ids":["https://openalex.org/I4210113297","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091179481","display_name":"Stefano Ermon","orcid":"https://orcid.org/0000-0003-0039-2887"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefano Ermon","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0039-2887","affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087676937","display_name":"Alfredo Garcia","orcid":"https://orcid.org/0000-0002-8902-6834"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alfredo Garcia","raw_affiliation_strings":["Department of Industrial and Systems Engineering, Texas A&M University, College Station, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-8902-6834","affiliations":[{"raw_affiliation_string":"Department of Industrial and Systems Engineering, Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100633783","display_name":"Mingyi Hong","orcid":"https://orcid.org/0000-0003-1263-9365"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingyi Hong","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA"],"raw_orcid":"https://orcid.org/0000-0003-1263-9365","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"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":0.7948106,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"43","issue":"3","first_page":"71","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.12790000438690186,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.12790000438690186,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.11569999903440475,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.04820000007748604,"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/language-of-mathematics","display_name":"Language of mathematics","score":0.5288000106811523},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.37529999017715454},{"id":"https://openalex.org/keywords/mathematical-model","display_name":"Mathematical model","score":0.351500004529953},{"id":"https://openalex.org/keywords/algorithm-design","display_name":"Algorithm design","score":0.32989999651908875},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.32600000500679016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6953999996185303},{"id":"https://openalex.org/C172347087","wikidata":"https://www.wikidata.org/wiki/Q3217196","display_name":"Language of mathematics","level":2,"score":0.5288000106811523},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.447299987077713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41670000553131104},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39579999446868896},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C76969082","wikidata":"https://www.wikidata.org/wiki/Q486902","display_name":"Mathematical model","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.2879999876022339},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.27709999680519104},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27309998869895935}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/msp.2026.3666824","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2026.3666824","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.531004011631012}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1999568555","https://openalex.org/W2033442452","https://openalex.org/W2100076918","https://openalex.org/W2763110165","https://openalex.org/W3023581195","https://openalex.org/W4241811150","https://openalex.org/W4389519291","https://openalex.org/W4402626746"],"related_works":[],"abstract_inverted_index":{"This":[0],"article":[1],"provides":[2],"an":[3],"introduction":[4],"to":[5,13,59,91],"the":[6,49],"mathematical":[7],"foundations":[8],"and":[9,23,41,64,79,81,99,109,116],"algorithmic":[10],"frameworks":[11],"used":[12],"align":[14],"large":[15],"language":[16],"models":[17],"(LLMs)":[18],"with":[19,37],"human":[20,38,55],"intentions,":[21],"preferences,":[22,56],"values.":[24],"We":[25,46,68],"discuss":[26,76],"standard":[27],"alignment":[28,107,118],"techniques,":[29],"such":[30],"as":[31,93],"supervised":[32],"fine-tuning":[33],"(SFT),":[34],"reinforcement":[35,61],"learning":[36,53,62],"feedback":[39],"(RLHF),":[40],"direct":[42],"preference":[43],"optimization":[44],"(DPO).":[45],"also":[47],"explore":[48],"theoretical":[50],"underpinnings":[51],"of":[52,106],"from":[54],"drawing":[57],"connections":[58],"inverse":[60],"(IRL),":[63],"discrete":[65],"choice":[66],"models.":[67],"present":[69],"state-of-the-art":[70],"algorithms":[71],"in":[72],"a":[73,94,103,110],"tutorial":[74],"style,":[75],"their":[77],"advantages":[78],"limitations,":[80],"offer":[82],"insights":[83],"into":[84],"practical":[85],"implementation.":[86],"Our":[87],"exposition":[88],"is":[89],"intended":[90],"serve":[92],"comprehensive":[95],"resource":[96],"for":[97,112],"researchers":[98],"practitioners,":[100],"providing":[101],"both":[102],"foundational":[104],"understanding":[105],"methodologies":[108],"framework":[111],"developing":[113],"more":[114],"robust":[115],"scalable":[117],"techniques.":[119]},"counts_by_year":[],"updated_date":"2026-07-06T08:01:05.025921","created_date":"2026-06-13T00:00:00"}