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：个性化对话代理能够提升对话质量并增强用户参与度。然而，现有模型常缺乏外部知识来恰当地关注用户个性，这一缺陷在心理健康支持、营养规划、文化敏感对话以及减少对话代理毒性行为等实际应用中尤为关键。为提升个性化回复的相关性与全面性，我们提出一种两步法：（1）选择性整合用户画像；（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（知识引导的个性化奖励调制模型），这是一款融合上述要素的动态对话代理。在包含真实世界地标个性化对话的FoCus基准数据集上，K-PERM取得了最先进性能。研究表明，基于K-PERM的回复可使当前最先进的大语言模型（GPT-3.5）性能提升10.5%，凸显了K-PERM在聊天机器人个性化中的重要作用。