2023/12/29 by Kanak Raj, Raj, Kanak, Kaushik Roy +5 · 1 citation
Computer Science · #AI in Service Interactions #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Persona Design and Applications #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2312.17748
openalex publication_date 2023/12/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.