{"id":"https://openalex.org/W7166805486","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1283","title":"HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing","display_name":"HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166805486","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1283"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1283","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1283","pdf_url":"https://aclanthology.org/2026.findings-acl.1283.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1283.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139720120","display_name":"Chengyu Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengyu Du","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139788072","display_name":"Xintao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xintao Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139799700","display_name":"Aili Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aili Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139848685","display_name":"Weiyuan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiyuan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139823312","display_name":"Rui Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087431853","display_name":"Junteng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junteng Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125121160","display_name":"Zishan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zishan Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008330501","display_name":"Rong Tian","orcid":"https://orcid.org/0000-0002-5191-9004"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076728540","display_name":"Zijun Sun","orcid":"https://orcid.org/0000-0001-5386-5495"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zijun Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139779327","display_name":"Yuhao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139785643","display_name":"Liheng Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liheng Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123241633","display_name":"Deming Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deming Ding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139826493","display_name":"Pengyu Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengyu Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139720915","display_name":"Yanghua Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanghua Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.79513778,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"25725","last_page":"25762"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3257000148296356,"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":0.3257000148296356,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.07259999960660934,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0551999993622303,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.43560001254081726},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.37709999084472656},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.3571000099182129},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.29429998993873596},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.2831999957561493}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5115000009536743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5077000260353088},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.43560001254081726},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3395000100135803},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1283","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1283","pdf_url":"https://aclanthology.org/2026.findings-acl.1283.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1283","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1283","pdf_url":"https://aclanthology.org/2026.findings-acl.1283.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6532108187675476,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166805486.pdf","grobid_xml":"https://content.openalex.org/works/W7166805486.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Chengyu":[0],"Du,":[1],"Xintao":[2],"Wang,":[3],"Aili":[4],"Chen,":[5],"Weiyuan":[6],"Li,":[7,19],"Rui":[8],"Xu,":[9],"Junteng":[10],"Liu,":[11],"Zishan":[12],"Huang,":[13],"Rong":[14],"Tian,":[15],"Zijun":[16],"Sun,":[17],"Yuhao":[18],"Liheng":[20],"Feng,":[21],"Deming":[22],"Ding,":[23],"Pengyu":[24],"Zhao,":[25],"Yanghua":[26],"Xiao.":[27],"Findings":[28],"of":[29],"the":[30],"Association":[31],"for":[32],"Computational":[33],"Linguistics:":[34],"ACL":[35],"2026.":[36,37]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
