作者位次 #5/14ACL 2026Findings· Findings of ACL
HER : Human-like Reasoning and Reinforcement Learning for LLM Role-playing
Chengyu Du · Xintao Wang · Aili Chen · Weiyuan Li · Rui Xu · Junteng Liu · Zishan Huang · Rong Tian · Zijun Sun · Yuhao Li · Liheng Feng · Deming Ding · Pengyu Zhao · Yanghua Xiao
摘要
LLM role-playing, i.e., using large language models (LLMs) to simulate specific personas, has emerged as a key capability in various applications, such as companionship, content creation, and digital games. While current models effectively capture character tones and knowledge, simulating the inn...