Personalizing conversational agents can enhance the quality of conversations and increase user engagement. However, they often lack external knowledge to appropriately tend to a user's persona. This is particularly crucial for practical applications like mental health support, nutrition planning, culturally sensitive conversations, or reducing toxic behavior in conversational agents. To enhance the relevance and comprehensiveness of personalized responses, we propose using a two-step approach that involves (1) selectively integrating user personas and (2) contextualizing the response with supplementing information from a background knowledge source. We develop K-PERM (Knowledge-guided PErsonalization with Reward Modulation), a dynamic conversational agent that combines these elements. K-PERM achieves state-of-the-art performance on the popular FoCus dataset, containing real-world personalized conversations concerning global landmarks. We show that using responses from K-PERM can improve performance in state-of-the-art LLMs (GPT 3.5) by 10.5%, highlighting the impact of K-PERM for personalizing chatbots.

翻译：个性化对话智能体能够提升对话质量并增强用户参与度，但其常因缺乏外部知识而难以恰当顾及用户角色特征，这对心理健康支持、营养规划、文化敏感性对话及减少对话智能体毒性行为等实际应用尤为关键。为提升个性化回复的相关性与全面性，我们提出采用包含两个步骤的方法：（1）选择性融合用户角色，（2）通过背景知识源补充信息对回复进行情境化。我们开发了K-PERM（知识引导的奖励调制个性化机制），这是一种融合上述要素的动态对话智能体。在包含真实世界个性化地标对话的主流FoCus数据集上，K-PERM取得了最优性能。实验表明，使用K-PERM生成的回复可使先进大语言模型（GPT 3.5）的性能提升10.5%，凸显了其在聊天机器人个性化中的重要作用。