研究用户性格情绪对对话生成的影响，发现负面情绪易导致对话僵硬。
Exploring Persona Sentiment Sensitivity in Personalized Dialogue Generation
- 按用户情绪极性分组生成对话，分析其差异
- 负面情绪用户对话过度强调个性，正面则更自然流畅
- 适合想提升对话自然度的对话系统开发者
个性化对话系统通过将用户特定人格特征融入大语言模型（LLMs）取得了显著进展。然而，人格情绪对对话质量的影响仍不明确。本文开展大规模实验，分析不同情绪极性的用户人格生成的对话表现。结果表明，负向情绪人格的对话会过度强调人格属性；正向情绪人格则选择性融合人格信息，交互更自然。此外，弱情绪或中性人格通常生成低质量对话。基于此，我们提出一种新方法，通过轮次生成策略、人格排序机制与情绪感知提示，显式建模人格极性。研究揭示了LLMs对人格情绪的敏感性，为构建更鲁棒、细腻的个性化对话系统提供指导。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。