{"id":"https://openalex.org/W4415850505","doi":"https://doi.org/10.1145/3773279","title":"A Survey on Human Preference Learning for Aligning Large Language Models","display_name":"A Survey on Human Preference Learning for Aligning Large Language Models","publication_year":2025,"publication_date":"2025-11-04","ids":{"openalex":"https://openalex.org/W4415850505","doi":"https://doi.org/10.1145/3773279"},"language":"en","primary_location":{"id":"doi:10.1145/3773279","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3773279","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","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/A5081665683","display_name":"Ruili Jiang","orcid":"https://orcid.org/0000-0002-6126-2317"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruili Jiang","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":"https://orcid.org/0000-0002-6126-2317","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006323375","display_name":"Kehai Chen","orcid":"https://orcid.org/0000-0002-4346-7618"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kehai Chen","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":"https://orcid.org/0000-0002-4346-7618","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101905617","display_name":"Xuefeng Bai","orcid":"https://orcid.org/0000-0001-7044-0683"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefeng Bai","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen)"],"raw_orcid":"https://orcid.org/0000-0001-7044-0683","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103341952","display_name":"Z. H. He","orcid":"https://orcid.org/0009-0007-8511-4398"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixuan He","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen)"],"raw_orcid":"https://orcid.org/0009-0007-8511-4398","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100657514","display_name":"Juntao Li","orcid":"https://orcid.org/0000-0002-6286-7529"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juntao Li","raw_affiliation_strings":["Soochow University"],"raw_orcid":"https://orcid.org/0000-0002-6286-7529","affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108053327","display_name":"Muyun Yang","orcid":"https://orcid.org/0000-0002-5940-0266"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Muyun Yang","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":"https://orcid.org/0000-0002-5940-0266","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101661008","display_name":"Tiejun Zhao","orcid":"https://orcid.org/0000-0003-4659-4935"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiejun Zhao","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":"https://orcid.org/0000-0003-4659-4935","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen)"],"raw_orcid":"https://orcid.org/0000-0003-1476-0273","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100402911","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-3895-5510"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen)"],"raw_orcid":"https://orcid.org/0000-0002-3895-5510","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5081665683"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":4.3465,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9488332,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"58","issue":"6","first_page":"1","last_page":"39"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.39730000495910645,"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/T10028","display_name":"Topic Modeling","score":0.39730000495910645,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.11860000342130661,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.051500000059604645,"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/preference","display_name":"Preference","score":0.7008000016212463},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.61080002784729},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6011999845504761},{"id":"https://openalex.org/keywords/human-language","display_name":"Human language","score":0.4805000126361847},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.46070000529289246},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.33799999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764999866485596},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.7008000016212463},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.61080002784729},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6011999845504761},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.4805000126361847},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.46070000529289246},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41190001368522644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.382099986076355},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36039999127388},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.28780001401901245},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2676999866962433}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3773279","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3773279","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7322739430","display_name":null,"funder_award_id":"2024A1515011205","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G972432731","display_name":null,"funder_award_id":"62276077, 62406091, U23B2055, 62350710797","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1155403144","https://openalex.org/W2027106130","https://openalex.org/W2069277547","https://openalex.org/W2119717200","https://openalex.org/W2149427297","https://openalex.org/W2154023516","https://openalex.org/W3022194887","https://openalex.org/W3100355250","https://openalex.org/W4223433337","https://openalex.org/W4230646247","https://openalex.org/W4389520260","https://openalex.org/W4390035079","https://openalex.org/W4398143508","https://openalex.org/W4401042689","https://openalex.org/W4402670092","https://openalex.org/W4402670418","https://openalex.org/W4402670760","https://openalex.org/W4402684060","https://openalex.org/W4403863303","https://openalex.org/W4404781253","https://openalex.org/W4404781537","https://openalex.org/W4404792842","https://openalex.org/W4411063470","https://openalex.org/W4412887808","https://openalex.org/W4412888166"],"related_works":[],"abstract_inverted_index":{"The":[0],"recent":[1],"surge":[2],"in":[3,28,37,53],"versatile":[4],"large":[5],"language":[6],"models":[7],"(LLMs)":[8],"demonstrates":[9],"remarkable":[10],"success":[11,24],"across":[12],"a":[13,34,58,64,123],"wide":[14],"range":[15],"of":[16,102],"contexts.":[17],"A":[18],"key":[19],"factor":[20],"contributing":[21],"to":[22,62,73],"this":[23,47],"is":[25],"LLM":[26,76,107],"alignment,":[27],"which":[29],"human":[30,44,54,81,93],"preference":[31,55,82,94],"learning":[32,56],"plays":[33],"decisive":[35],"role":[36],"steering":[38],"the":[39,51,112],"models\u2019":[40],"capabilities":[41],"toward":[42],"fulfilling":[43],"objectives.":[45],"In":[46],"survey,":[48],"we":[49,79,110],"review":[50],"progress":[52],"within":[57],"unified":[59],"framework,":[60],"aiming":[61],"provide":[63],"comprehensive":[65],"perspective":[66],"on":[67,85,126],"established":[68],"methodologies":[69],"while":[70],"exploring":[71],"avenues":[72],"further":[74],"advance":[75],"alignment.":[77,108],"Specifically,":[78],"categorize":[80],"feedback":[83],"based":[84],"data":[86],"sources":[87],"and":[88,96,98,115,129],"formats,":[89],"summarize":[90],"techniques":[91],"for":[92,106,119],"modeling":[95],"usage,":[97],"present":[99],"an":[100],"overview":[101],"prevailing":[103],"evaluation":[104],"protocols":[105],"Finally,":[109],"discuss":[111],"existing":[113],"challenges":[114],"identify":[116],"potential":[117],"directions":[118],"future":[120],"research,":[121],"with":[122],"particular":[124],"emphasis":[125],"generalizability,":[127],"transferability,":[128],"controllability.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-07T23:40:59.601060","created_date":"2025-11-04T00:00:00"}
