通过动态优化角色人格，让AI扮演更贴合真实人类行为。
DPRF: A Generalizable Dynamic Persona Refinement Framework for Optimizing Behavior Alignment Between Personalized LLM Role-Playing Agents and Humans
- 基于认知偏差检测，迭代更新角色设定以贴近真人表现。
- 在4类场景中显著提升角色行为与真人的一致性，跨模型通用。
- 适合需要高真实感角色模拟的用户仿真、社会研究等场景。
新兴的大语言模型角色扮演代理（LLM RPAs）旨在模拟个体人类行为，但其人格真实性常因手动构建的角色档案（如挑选性信息和性格特征）而受损，且缺乏与目标个体行为的验证对齐。为此，本文提出动态人格精炼框架（DPRF），通过迭代识别生成行为与人类真实行为之间的认知偏差（采用自由表述或理论支撑的结构化分析），并据此优化人格档案以减少这些差异。我们在四个多样化的行为预测场景——正式辩论、带有心理健康问题的社交媒体发文、公开访谈和电影评论——上评估了五个LLM的DPRF效果。结果表明，相较于基线人格档案，DPRF能显著提升行为对齐度，并在不同模型与场景间具备良好泛化能力。本工作为构建高保真人格档案提供了稳健方法，可增强用户模拟、社会研究及个性化AI等下游应用的有效性。
原文摘要 · Abstract (English)
The emerging large language model role-playing agents (LLM RPAs) aim to simulate individual human behaviors, but the persona fidelity is often undermined by manually-created profiles (e.g., cherry-picked information and personality characteristics) without validating the alignment with the target individuals. To address this limitation, our work introduces the Dynamic Persona Refinement Framework (DPRF). DPRF aims to optimize the alignment of LLM RPAs' behaviors with those of target individuals by iteratively identifying the cognitive divergence, either through free-form or theory-grounded, structured analysis, between generated behaviors and human ground truth, and refining the persona profile to mitigate these divergences. We evaluate DPRF with five LLMs on four diverse behavior-prediction scenarios: formal debates, social media posts with mental health issues, public interviews, and movie reviews. DPRF can consistently improve behavioral alignment considerably over baseline personas and generalizes across models and scenarios. Our work provides a robust methodology for creating high-fidelity persona profiles and enhancing the validity of downstream applications, such as user simulation, social studies, and personalized AI.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。