PersonaKit (PK): 一种用于用户测试多样化角色的即插即用平台
PersonaKit (PK): A Plug-and-Play Platform for User Testing Diverse Roles in Full-Duplex Dialogue
AI总结：
本文提出PersonaKit平台，通过直观的JSON配置定义角色并测试不同的轮流策略，验证了复杂社会语言行为的研究框架。
摘要：
随着口语对话系统从传统助手角色扩展到涵盖权威教师、不合作商人或分心工作者等多样化角色，它们需要独特的、人类般的轮流行为以保持心理沉浸感。然而，当前全双工系统在重叠语音期间通常默认采用僵化的、过度让步的『总是让步』策略，这严重破坏了非让步角色的一致性。通过实证用户研究评估替代的、角色特定的轮流策略具有挑战性，因为构建实时全双工测试环境需要大量工程工作。为此，我们提出了PersonaKit (PK)，一个开源、低延迟的网页平台，用于快速原型设计和评估对话代理。通过直观的JSON配置，研究人员可以定义角色、指定概率性中断处理行为（例如让步、保持、桥接或覆盖），并自动部署比较性A/B调查。通过实地评估8种不同的角色，我们证明PersonaKit提供了一个可扩展、端到端的框架，用于研究下一代口语代理中的复杂社会语言行为。
英文摘要：
As spoken dialogue systems expand beyond traditional assistant roles to encompass diverse personas -- such as authoritative instructors, uncooperative merchants, or distracted workers -- they require distinct, human-like turn-taking behaviors to maintain psychological immersion. However, current full-duplex systems often default to a rigid, overly accommodating ``always-yield'' policy during overlapping speech, which severely undermines character consistency for non-submissive roles. Evaluating alternative, persona-specific turn-taking strategies through empirical user studies is challenging because building real-time full-duplex test environments requires substantial engineering overhead. To address this, we present PersonaKit (PK), an open-source, low-latency web platform for the rapid prototyping and evaluation of conversational agents. Using intuitive JSON configurations, researchers can define personas, specify probabilistic interruption-handling behaviors (e.g., yield, hold, bridge, or override), and automatically deploy comparative A/B surveys. Through an in-the-wild evaluation with 8 distinct personas, we demonstrate that PersonaKit provides an extensible, end-to-end framework for studying complex sociolinguistic behaviors in next-generation spoken agents.
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。
