Exploring Persona Sentiment Sensitivity in Personalized Dialogue Generation
This work addresses the issue of persona sentiment sensitivity for developers of personalized dialogue systems, offering incremental insights and guidance for more robust systems.
The paper tackled the problem of how persona sentiment affects dialogue quality in personalized dialogue systems, finding that negatively polarized users lead to overemphasis on persona attributes, positively polarized ones yield smoother interactions, and neutral personas produce lower-quality dialogues, with a proposed approach that improves performance by explicitly accounting for persona polarity.
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. In contrast, positively polarized profiles yield dialogues that selectively incorporate persona information, resulting in smoother 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 and sentiment-aware prompting. 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.