构建无偏对话人格模型，提升个性化交互的公平性与可靠性
UPCS: Unbiased Persona Construction for Dialogue Generation
- 将人物描述分为8个维度，系统化识别与缓解偏见
- 实验显示在准确率、多样性及用户满意度上全面优于现有方法
- 适合关注生成内容公平性的对话系统研究者使用
叙事系统（如对话和故事生成系统）常利用人物档案增强个性化交互。现有角色描述普遍存在偏见，威胁系统完整性与公平性。为此，本文提出UPCS框架，将角色描述划分为八个维度，并集成偏见缓解策略。实验结果表明，UPCS在准确性、多样性、偏见消除与用户满意度方面均表现更优，显著推进了可靠叙事系统中人物构建的发展。
原文摘要 · Abstract (English)
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.
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。