Abstract:Personalized dialogue systems have advanced considerably with the integration of user-specific personas into large language models (LLMs). However, while LLMs can effectively generate personalized responses, the influence of persona sentiment on dialogue quality remains underexplored. In this work, we conduct a large-scale analysis of dialogues generated using a range of polarized user profiles. Our experiments reveal that dialogues involving negatively polarized users tend to overemphasize persona attributes, leading to increased entailment and contradiction instances and lower overall coherence. In contrast, positively polarized profiles yield dialogues that selectively incorporate persona information, resulting in smoother and more coherent interactions. Furthermore, we find that personas with weak or neutral sentiment generally produce lower-quality dialogues. Motivated by these findings, we propose a dialogue generation approach that explicitly accounts for persona polarity by combining a turn-based generation strategy with a profile ordering mechanism. Our study provides new insights into the sensitivity of LLMs to persona sentiment and offers guidance for developing more robust and nuanced personalized dialogue systems.