PicPersona-TOD：用于在任务型对话中通过图像人设个性化话语风格的数据集
PicPersona-TOD : A Dataset for Personalizing Utterance Style in Task-Oriented Dialogue with Image Persona
AI总结：
本文提出PicPersona-TOD数据集，利用用户图像作为人设，结合第一印象、策略引导和外部知识，实现任务型对话中的个性化回复，并引入NLG模型Pictor，在未见领域表现稳健。
摘要：
任务型对话（TOD）系统旨在通过自然语言交互满足用户请求，然而现有系统常常生成通用、单调的回复，缺乏个性，且无法适应用户的个人属性。为解决这一问题，我们引入了PicPersona-TOD，这是一个新颖的数据集，将用户图像作为人设的一部分，从而能够针对用户特定因素（如年龄或情绪背景）定制个性化回复。这得益于第一印象、对话策略引导的提示以及利用外部知识来减少幻觉。人工评估证实，我们的数据集提升了用户体验，个性化回复有助于实现更具吸引力的交互。此外，我们引入了一个新的自然语言生成（NLG）模型Pictor，它不仅能够个性化回复，还在未见领域展现出稳健的性能。https://github.com/JihyunLee1/PicPersona
英文摘要：
Task-Oriented Dialogue (TOD) systems are designed to fulfill user requests through natural language interactions, yet existing systems often produce generic, monotonic responses that lack individuality and fail to adapt to users' personal attributes. To address this, we introduce PicPersona-TOD, a novel dataset that incorporates user images as part of the persona, enabling personalized responses tailored to user-specific factors such as age or emotional context. This is facilitated by first impressions, dialogue policy-guided prompting, and the use of external knowledge to reduce hallucinations. Human evaluations confirm that our dataset enhances user experience, with personalized responses contributing to a more engaging interaction. Additionally, we introduce a new NLG model, Pictor, which not only personalizes responses, but also demonstrates robust performance across unseen domains https://github.com/JihyunLee1/PicPersona.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
