UPCS：面向对话生成的无偏人物画像构建
UPCS: Unbiased Persona Construction for Dialogue Generation
AI总结：
针对叙事系统中人物画像存在偏见的问题，本文提出UPCS框架，将角色描述划分为八个维度并融入偏见缓解策略，在准确性、多样性、偏见消除和用户满意度上取得显著提升。
摘要：
叙事系统，如对话和故事讲述系统，通常利用人物画像来增强个性化交互。现有的人物画像经常表现出偏见，对系统的完整性和公平性构成风险。为解决这一问题，我们提出了UPCS框架，该框架将角色描述分为八个维度，并包含偏见缓解策略。实验结果表明，UPCS在准确性、多样性、偏见消除和用户满意度方面具有优越性，标志着面向可靠叙事系统的人物画像构建取得了重大进展。
英文摘要：
Narrative systems, such as dialogue and storytelling systems, often utilize persona profiles to enhance personalized interactions. Existing persona profiles frequently exhibit biases, posing risks to system integrity and fairness. To address this, we introduce the UPCS framework, which categorizes character descriptions into eight dimensions, including bias mitigation strategies. Experimental results demonstrate UPCS's superiority in accuracy, diversity, bias elimination, and user satisfaction, marking a significant advancement in persona construction for reliable narrative systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
