{"id":"https://openalex.org/W7161798856","doi":"https://doi.org/10.1016/j.neucom.2026.133996","title":"Mixed-policy preference optimization with self-generated non-preferred responses and off-policy preference distillation","display_name":"Mixed-policy preference optimization with self-generated non-preferred responses and off-policy preference distillation","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W7161798856","doi":"https://doi.org/10.1016/j.neucom.2026.133996"},"language":"en","primary_location":{"id":"doi:10.1016/j.neucom.2026.133996","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133996","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","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/A5112223261","display_name":"Binrui Wang","orcid":"https://orcid.org/0000-0002-8955-4055"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]},{"id":"https://openalex.org/I4210141165","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64","country_code":"TW","type":"government","lineage":["https://openalex.org/I4210141165","https://openalex.org/I4405257903"]}],"countries":["CN","TW"],"is_corresponding":false,"raw_author_name":"Binrui Wang","raw_affiliation_strings":["Engineering Research Center of Digital Community, Ministry of Education, Pingleyuan, Beijing, 100124, China","School of Computer Science, Beijing University of Technology, Pingleyuan, Beijing, 100124, China"],"raw_orcid":"https://orcid.org/0000-0001-9851-5528","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Digital Community, Ministry of Education, Pingleyuan, Beijing, 100124, China","institution_ids":["https://openalex.org/I4210141165"]},{"raw_affiliation_string":"School of Computer Science, Beijing University of Technology, Pingleyuan, Beijing, 100124, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070601883","display_name":"Z Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]},{"id":"https://openalex.org/I4210141165","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64","country_code":"TW","type":"government","lineage":["https://openalex.org/I4210141165","https://openalex.org/I4405257903"]}],"countries":["CN","TW"],"is_corresponding":false,"raw_author_name":"Zikai Wang","raw_affiliation_strings":["Engineering Research Center of Digital Community, Ministry of Education, Pingleyuan, Beijing, 100124, China","School of Computer Science, Beijing University of Technology, Pingleyuan, Beijing, 100124, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Research Center of Digital Community, Ministry of Education, Pingleyuan, Beijing, 100124, China","institution_ids":["https://openalex.org/I4210141165"]},{"raw_affiliation_string":"School of Computer Science, Beijing University of Technology, Pingleyuan, Beijing, 100124, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136587754","display_name":"Yongping Du","orcid":"https://orcid.org/0000-0001-6867-2063"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]},{"id":"https://openalex.org/I4210141165","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64","country_code":"TW","type":"government","lineage":["https://openalex.org/I4210141165","https://openalex.org/I4405257903"]}],"countries":["CN","TW"],"is_corresponding":true,"raw_author_name":"Yongping Du","raw_affiliation_strings":["Engineering Research Center of Digital Community, Ministry of Education, Pingleyuan, Beijing, 100124, China","School of Computer Science, Beijing University of Technology, Pingleyuan, Beijing, 100124, China"],"raw_orcid":"https://orcid.org/0000-0001-6867-2063","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Digital Community, Ministry of Education, Pingleyuan, Beijing, 100124, China","institution_ids":["https://openalex.org/I4210141165"]},{"raw_affiliation_string":"School of Computer Science, Beijing University of Technology, Pingleyuan, Beijing, 100124, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136523795","display_name":"Mingyang Li","orcid":"https://orcid.org/0009-0006-4753-428X"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]},{"id":"https://openalex.org/I4210141165","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64","country_code":"TW","type":"government","lineage":["https://openalex.org/I4210141165","https://openalex.org/I4405257903"]}],"countries":["CN","TW"],"is_corresponding":false,"raw_author_name":"Mingyang Li","raw_affiliation_strings":["Engineering Research Center of Digital Community, Ministry of Education, Pingleyuan, Beijing, 100124, China","School of Computer Science, Beijing University of Technology, Pingleyuan, Beijing, 100124, China"],"raw_orcid":"https://orcid.org/0009-0006-4753-428X","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Digital Community, Ministry of Education, Pingleyuan, Beijing, 100124, China","institution_ids":["https://openalex.org/I4210141165"]},{"raw_affiliation_string":"School of Computer Science, Beijing University of Technology, Pingleyuan, Beijing, 100124, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5136587754"],"corresponding_institution_ids":["https://openalex.org/I37796252","https://openalex.org/I4210141165"],"apc_list":{"value":2470,"currency":"USD","value_usd":2470},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65099421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"695","issue":null,"first_page":"133996","last_page":"133996"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.11710000038146973,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.11710000038146973,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.0828000009059906,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.06809999793767929,"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":0.8105999827384949},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6201000213623047},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5705999732017517},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.49219998717308044},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.47760000824928284},{"id":"https://openalex.org/keywords/preference-elicitation","display_name":"Preference elicitation","score":0.3635999858379364}],"concepts":[{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.8105999827384949},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6502000093460083},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6201000213623047},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5705999732017517},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.49219998717308044},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48829999566078186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4853000044822693},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.47760000824928284},{"id":"https://openalex.org/C2777868144","wikidata":"https://www.wikidata.org/wiki/Q7239817","display_name":"Preference elicitation","level":3,"score":0.3635999858379364},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3206000030040741},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.2741999924182892}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.neucom.2026.133996","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133996","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5389372110366821}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4405908042"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-05-27T06:14:07.914337","created_date":"2026-05-21T00:00:00"}
