PARAN: Persona-Augmented Review ANswering system on Food Delivery Review Dataset
This work addresses the problem of generic automated responses for food delivery platforms, offering a method to enhance engagement without fine-tuning, though it is incremental as it builds on existing LLM capabilities.
The paper tackles the challenge of generating personalized review responses in food delivery platforms by proposing a two-stage prompting framework that infers explicit and implicit personas from short review texts to produce user-tailored replies, evaluated on a real-world Korean dataset with improvements in relevance and personalization.
Personalized review response generation presents a significant challenge in domains where user information is limited, such as food delivery platforms. While large language models (LLMs) offer powerful text generation capabilities, they often produce generic responses when lacking contextual user data, reducing engagement and effectiveness. In this work, we propose a two-stage prompting framework that infers both explicit (e.g., user-stated preferences) and implicit (e.g., demographic or stylistic cues) personas directly from short review texts. These inferred persona attributes are then incorporated into the response generation prompt to produce user-tailored replies. To encourage diverse yet faithful generations, we adjust decoding temperature during inference. We evaluate our method using a real-world dataset collected from a Korean food delivery app, and assess its impact on precision, diversity, and semantic consistency. Our findings highlight the effectiveness of persona-augmented prompting in enhancing the relevance and personalization of automated responses without requiring model fine-tuning.