TOP:A New Target-Audience Oriented Content Paraphrase Task

TL;DR

This paper introduces a novel content paraphrasing task tailored to target audiences, aiming to enhance recommendation systems by customizing content based on user interests using large language and vision models.

Contribution

The paper defines the Target-Audience Oriented Content Paraphrase task, proposes a framework, creates datasets, and provides baseline results using LLMs and LVMs.

Findings

Baseline results demonstrate the feasibility of the proposed framework.

Datasets for target-audience content paraphrasing are created.

The approach improves content relevance for specific user groups.

Abstract

Recommendation systems usually recommend the existing contents to different users. However, in comparison to static recommendation methods, a recommendation logic that dynamically adjusts based on user interest preferences may potentially attract a larger user base. Thus, we consider paraphrasing existing content based on the interests of the users to modify the content to better align with the preferences of users. In this paper, we propose a new task named Target-Audience Oriented Content Paraphrase aims to generate more customized contents for the target audience. We introduce the task definition and the corresponding framework for the proposed task and the creation of the corresponding datasets. We utilize the Large Language Models (LLMs) and Large Vision Models (LVMs) to accomplish the base implementation of the TOP framework and provide the referential baseline results for the proposed task.