{"id":"https://openalex.org/W4404822917","doi":"https://doi.org/10.1007/978-981-97-8367-0_33","title":"Prior Constraints-Based Reward Model Training for\u00a0Aligning Large Language Models","display_name":"Prior Constraints-Based Reward Model Training for\u00a0Aligning Large Language Models","publication_year":2024,"publication_date":"2024-11-28","ids":{"openalex":"https://openalex.org/W4404822917","doi":"https://doi.org/10.1007/978-981-97-8367-0_33"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-97-8367-0_33","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-97-8367-0_33","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":"book-chapter","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/A5007916294","display_name":"Hang Zhou","orcid":"https://orcid.org/0000-0002-7524-8751"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hang Zhou","raw_affiliation_strings":["NLP Lab, School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"NLP Lab, School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004011841","display_name":"Chenglong Wang","orcid":"https://orcid.org/0000-0002-5785-7027"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Wang","raw_affiliation_strings":["NLP Lab, School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"NLP Lab, School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102775522","display_name":"Yimin Hu","orcid":"https://orcid.org/0000-0002-0601-218X"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yimin Hu","raw_affiliation_strings":["NLP Lab, School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"NLP Lab, School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100600701","display_name":"Tong Xiao","orcid":"https://orcid.org/0000-0002-5842-6501"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Xiao","raw_affiliation_strings":["NLP Lab, School of Computer Science and Engineering, Northeastern University, Shenyang, China","NiuTrans Research, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"NLP Lab, School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"NiuTrans Research, Shenyang, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101997180","display_name":"Chunliang Zhang","orcid":"https://orcid.org/0000-0002-4382-2413"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunliang Zhang","raw_affiliation_strings":["NLP Lab, School of Computer Science and Engineering, Northeastern University, Shenyang, China","NiuTrans Research, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"NLP Lab, School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"NiuTrans Research, Shenyang, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100370145","display_name":"Jingbo Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingbo Zhu","raw_affiliation_strings":["NLP Lab, School of Computer Science and Engineering, Northeastern University, Shenyang, China","NiuTrans Research, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"NLP Lab, School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"NiuTrans Research, Shenyang, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5007916294"],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47238505,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"555","last_page":"570"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9839000105857849,"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":0.9839000105857849,"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":0.964900016784668,"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/computer-science","display_name":"Computer science","score":0.879597544670105},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6487469673156738},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5228248834609985},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4483654201030731},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37777382135391235},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.33341503143310547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.879597544670105},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6487469673156738},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5228248834609985},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4483654201030731},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37777382135391235},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.33341503143310547},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-97-8367-0_33","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-97-8367-0_33","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2013784666","https://openalex.org/W4212901515","https://openalex.org/W4226278401","https://openalex.org/W4378468563","https://openalex.org/W4379474731","https://openalex.org/W4402670121","https://openalex.org/W6600384961","https://openalex.org/W6600710202","https://openalex.org/W6601848475","https://openalex.org/W6603292657","https://openalex.org/W6702248584","https://openalex.org/W6814003322"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W3204019825"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}