arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2609.21349cs.CLcs.AI

从记忆到行为:面向社交媒体影响者的行为感知角色扮演框架

From Memory to Behavior: A Behavior-Aware Role-Playing Framework for Social Media Influencers

Ji-Lun Peng, Yi-Zhen Zhang, Chun-Nan Chou, Yun-Nung Chen

首次发表
浏览论文内容

中文总结 AI 辅助

提出行为感知角色扮演框架,通过情境-内部状态-行为人格方法及带参考的评估协议,提升LLM对真实个体和虚构角色的模仿保真度,并在社交媒体回复任务中超越现有基线。

中文摘要 AI 辅助

大型语言模型在作为真实个体的角色扮演代理方面展现出强大潜力,但忠实的模仿仍具挑战性。现有的基于上下文学习的方法无法捕捉个体在不同情境下的反应方式。此外,基于LLM的评估对于不知名个体而言较为困难。为应对这些挑战,我们提出了“情境--内部状态--行为人格”方法,以纳入情境依赖的行为策略。我们进一步设计了一种评估协议,为LLM评估者提供关于被模仿个体的参考资料。我们在一个新构建的数据集上评估了我们的方法,该数据集用于社交媒体回复生成任务。实验结果表明,我们提出的方法优于最先进的基于ICL的基线方法,同时我们的评估协议与人类判断达到中等程度的相关性。此外,在虚构角色基准上的实验表明,我们提出的方法不仅适用于社交媒体场景。这些发现表明,纳入行为信息可广泛提升对社交媒体上真实个体或虚构角色进行角色扮演的保真度。

英文摘要

Large language models have shown strong potential as role-playing agents for real individuals, yet faithful impersonating remains challenging. Existing in-context learning-based methods fail to capture how individuals react under different situations. In addition, LLM-based evaluation is difficult for obscure individuals. To address these challenges, we propose Situation--Internal state--Behavior Persona method to incorporate situation-dependent behavioral strategies. We further design an evaluation protocol that provides LLM evaluators with references about the impersonated individual. We evaluate our approach on a newly constructed dataset for the task of generating replies on social media. Experimental results show that our proposed method outperforms state-of-the-art ICL-based baselines, while our evaluation protocol achieves moderate correlation with human judgment. Besides, experiments on fictional-character benchmarks demonstrate that our proposed method is applicable beyond the social media setting. These findings suggest that incorporating behavioral information broadly improves the fidelity of role-playing for real individuals on social media or fictional characters.

发表机构

  • CMoney Technology Corporation(CMoney科技公司)
  • National Taiwan University(国立台湾大学)

机构由 AI 辅助整理,请以论文原文为准。

补充信息

↑