{"id":"https://openalex.org/W4412945115","doi":"https://doi.org/10.18653/v1/2025.acl-long.794","title":"Mutual-Taught for Co-adapting Policy and Reward Models","display_name":"Mutual-Taught for Co-adapting Policy and Reward Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945115","doi":"https://doi.org/10.18653/v1/2025.acl-long.794"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.794","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.794","pdf_url":"https://aclanthology.org/2025.acl-long.794.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.794.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101107477","display_name":"Tianyuan Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyuan Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Canbin Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Canbin Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101262140","display_name":"Fanqi Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fanqi Wan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100664782","display_name":"Li Zhong","orcid":"https://orcid.org/0000-0003-1070-280X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Longguang Zhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665678","display_name":"Ziyi Yang","orcid":"https://orcid.org/0000-0002-7461-377X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyi Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108481711","display_name":"Weizhou Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weizhou Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040062188","display_name":"Xiaojun Quan","orcid":"https://orcid.org/0000-0002-8385-1083"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaojun Quan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101502057","display_name":"Ming Yan","orcid":"https://orcid.org/0000-0002-1751-2788"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26651601,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16285","last_page":"16298"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11508","display_name":"Corporate Taxation and Avoidance","score":0.8001999855041504,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11508","display_name":"Corporate Taxation and Avoidance","score":0.8001999855041504,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5895133018493652}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5895133018493652}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.794","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.794","pdf_url":"https://aclanthology.org/2025.acl-long.794.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.794","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.794","pdf_url":"https://aclanthology.org/2025.acl-long.794.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4399999976158142,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G6792809764","display_name":null,"funder_award_id":"62176270","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7447199816","display_name":null,"funder_award_id":"2023A1515012832","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945115.pdf","grobid_xml":"https://content.openalex.org/works/W4412945115.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Tianyuan":[0],"Shi,":[1],"Canbin":[2],"Huang,":[3],"Fanqi":[4],"Wan,":[5],"Longguang":[6],"Zhong,":[7],"Ziyi":[8],"Yang,":[9],"Weizhou":[10],"Shen,":[11],"Xiaojun":[12],"Quan,":[13],"Ming":[14],"Yan.":[15],"Proceedings":[16],"of":[17,22],"the":[18,23],"63rd":[19],"Annual":[20],"Meeting":[21],"Association":[24],"for":[25],"Computational":[26],"Linguistics":[27],"(Volume":[28],"1:":[29],"Long":[30],"Papers).":[31],"2025.":[32]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
