PicPersona-TOD : A Dataset for Personalizing Utterance Style in Task-Oriented Dialogue with Image Persona
Journal:
arXiv
Published Date:
Apr 24, 2025
Abstract
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.
