用用户图像个性化任务对话，让回复更自然有个性。
PicPersona-TOD : A Dataset for Personalizing Utterance Style in Task-Oriented Dialogue with Image Persona
- 用图像作为人物属性，生成符合用户特征的对话
- 人工评估显示个性化回复显著提升交互体验
- 适合研究个性化对话系统或人机交互的学者
任务导向对话（TOD）系统通过自然语言交互完成用户请求，但现有系统常产生通用、单调的回复，缺乏个性且无法适应用户个人特征。为此，我们提出 PicPersona-TOD，一个新数据集，将用户图像作为人物属性，实现基于年龄、情绪等个人因素的个性化回复。该方法结合第一印象、对话策略引导提示及外部知识，减少幻觉。人工评估证实，个性化回复显著提升用户体验。此外，我们还推出新文本生成模型 Pictor，不仅支持个性化，还在未见领域表现出强泛化能力。项目代码已开源：https://github.com/JihyunLee1/PicPersona。
原文摘要 · Abstract (English)
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.
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。