Panoramic Interests: Stylistic-Content Aware Personalized Headline Generation

TL;DR

This paper introduces SCAPE, a novel framework for personalized news headline generation that incorporates both content and stylistic preferences using large language models and contrastive learning, leading to improved personalization.

Contribution

SCAPE is the first to integrate stylistic and content preferences for personalized headlines through a hierarchical fusion network with LLM collaboration.

Findings

SCAPE outperforms baseline methods on PENS dataset.

Incorporating stylistic preferences enhances headline personalization.

Contrastive learning improves interest modeling accuracy.

Abstract

Personalized news headline generation aims to provide users with attention-grabbing headlines that are tailored to their preferences. Prevailing methods focus on user-oriented content preferences, but most of them overlook the fact that diverse stylistic preferences are integral to users' panoramic interests, leading to suboptimal personalization. In view of this, we propose a novel Stylistic-Content Aware Personalized Headline Generation (SCAPE) framework. SCAPE extracts both content and stylistic features from headlines with the aid of large language model (LLM) collaboration. It further adaptively integrates users' long- and short-term interests through a contrastive learning-based hierarchical fusion network. By incorporating the panoramic interests into the headline generator, SCAPE reflects users' stylistic-content preferences during the generation process. Extensive experiments on the real-world dataset PENS demonstrate the superiority of SCAPE over baselines.