作者位次 #7/8ACL 2026Findings· Findings of ACL
R ole CDE : Benchmarking and Mitigating Role–Alignment Trade-offs in Role-Playing Agents
Huayi Lai · Shichao Song · Simin Niu · Hanyu Wang · Jiawei Yang · Zhouxing Wang · Zhiqiang Yin · Xun Liang
摘要
Role-playing agents(RPAs) are widely used to steer large language models(LLMs) toward role-consistent behavior, yet existing benchmarks mainly evaluate surface-level fidelity and offer limited insight into decision making under role–alignment value conflicts. To address this gap, we introduce Rol...