Reinforcement Learning-Based Attribute Alignment for Role-Playing of LLMs.

Jiayang Fan|Ting Bai


Anthology ID:DBLP:conf/ccir/FanB25
Volume:Information Retrieval - 31st China Conference, CCIR 2025, Shihezi, China, August 15-17, 2025, Revised Selected Papers
Year:2025
Venue:China Conference on Information Retrieval (CCIR)
Publisher:Springer
Pages:13-25
URL:https://doi.org/10.1007/978-981-95-5637-3_2
DOI:https://doi.org/10.1007/978-981-95-5637-3_2
DBLP:conf/ccir/FanB25
BibTeX:
@inproceedings{fan-2025-reinforcement, author = {Jiayang Fan and Ting Bai}, editor = {Zhigang Li and Yanyan Lan and Zhumin Chen}, title = {{Reinforcement Learning-Based Attribute Alignment for Role-Playing of LLMs}}, booktitle = {{Information Retrieval - 31st China Conference, CCIR 2025, Shihezi, China, August 15-17, 2025, Revised Selected Papers}}, series = {Lecture Notes in Computer Science}, volume = {16369}, pages = {13--25}, publisher = {Springer}, year = {2025}, url = {https://doi.org/10.1007/978-981-95-5637-3_2}, doi = {https://doi.org/10.1007/978-981-95-5637-3_2} }