{"id":"https://openalex.org/W7169596520","doi":"https://doi.org/10.1007/978-981-92-3394-6_16","title":"PSPO: Trainable Potential-Based Reward Shaping with Internal Model Signals for Post-Training Policy Optimization of Large Language Models","display_name":"PSPO: Trainable Potential-Based Reward Shaping with Internal Model Signals for Post-Training Policy Optimization of Large Language Models","publication_year":2026,"publication_date":"2026-07-17","ids":{"openalex":"https://openalex.org/W7169596520","doi":"https://doi.org/10.1007/978-981-92-3394-6_16"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-92-3394-6_16","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-92-3394-6_16","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","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/A5027369574","display_name":"Miaobo Hu","orcid":"https://orcid.org/0000-0002-6417-3280"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miaobo Hu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, 100092, China","School of Cyber Security, University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":"https://orcid.org/0000-0002-6417-3280","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, 100092, China","institution_ids":["https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141088985","display_name":"Bokun Wang","orcid":"https://orcid.org/0009-0007-5519-6222"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bokun Wang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, 100092, China","School of Cyber Security, University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":"https://orcid.org/0009-0007-5519-6222","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, 100092, China","institution_ids":["https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141078052","display_name":"Shuhao Hu","orcid":"https://orcid.org/0009-0008-0501-8652"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhao Hu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, 100092, China","School of Cyber Security, University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":"https://orcid.org/0009-0008-0501-8652","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, 100092, China","institution_ids":["https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141063441","display_name":"Ruohan Wang","orcid":"https://orcid.org/0009-0000-9495-0389"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruohan Wang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, 100092, China","School of Cyber Security, University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":"https://orcid.org/0009-0000-9495-0389","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, 100092, China","institution_ids":["https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101903908","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-1069-4830"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, 100092, China"],"raw_orcid":"https://orcid.org/0000-0002-1069-4830","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, 100092, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101065849","display_name":"Xiaobo Guo","orcid":"https://orcid.org/0009-0007-2672-6650"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaobo Guo","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, 100092, China"],"raw_orcid":"https://orcid.org/0009-0007-2672-6650","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, 100092, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051666209","display_name":"Daren Zha","orcid":"https://orcid.org/0009-0002-6042-3454"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daren Zha","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, 100092, China"],"raw_orcid":"https://orcid.org/0009-0002-6042-3454","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, 100092, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076518693","display_name":"Jun Xiao","orcid":"https://orcid.org/0000-0002-1799-3948"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xiao","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":"https://orcid.org/0000-0002-1799-3948","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101065849"],"corresponding_institution_ids":["https://openalex.org/I4210156404"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"182","last_page":"193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45680001378059387},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.29100000858306885},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.26669999957084656},{"id":"https://openalex.org/keywords/internal-model","display_name":"Internal model","score":0.2630999982357025},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.2624000012874603}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8744000196456909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5123000144958496},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45680001378059387},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.319599986076355},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28529998660087585},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C28427503","wikidata":"https://www.wikidata.org/wiki/Q13580300","display_name":"Internal model","level":3,"score":0.2630999982357025},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.257099986076355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-92-3394-6_16","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-92-3394-6_16","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W4415796274","https://openalex.org/W7133208539"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-19T05:54:51.957546","created_date":"2026-07-18T00:00:00"}
