Generative News Recommendation
Keywords: News Recommendation; Generative Recommendation
TL;DR: A novel generative news recommendation paradigm
Abstract: Most existing news recommendation methods tackle this task by conducting semantic matching between candidate news and user representation produced by past clicked news. However, they ignore the higher-level associative relationships between news, and building these relationships typically requires common-sense knowledge and reasoning ability. And the definition of these methods dictates that they can only deliver news articles as-is. On the contrary, integrating several relevant news into a coherent narrative would assist users in gaining a quicker and more comprehensive understanding of events. In this paper, we propose a novel generative news recommendation paradigm that includes two steps: (1) Leveraging the internal knowledge and reasoning capabilities of the Large Language Model (LLM) to perform high-level matching between candidate news and user representation; (2) Generating a coherent and logically structured narrative based on the associations between related news and user interests, thus engaging users in further reading of the news. Specifically, we propose Generative News Recommendation (GNR). First, we compose the multi-level representation of news and users by leveraging LLM to generate theme-level representations and combine them with semantic-level representations. Next, in order to generate a coherent narrative, we explore the news relationship and filter the related news according to the user preference. Finally, we propose a novel training method named UIFT to train the LLM to fuse the multiple related news in a coherent narrative.
Extensive experiments show that GNR can improve the recommendation accuracy and eventually generate more personalized and factually consistent narratives.
Track: User Modeling and Recommendation
Submission Guidelines Scope: Yes
Submission Guidelines Blind: Yes
Submission Guidelines Format: Yes
Submission Guidelines Limit: Yes
Submission Guidelines Authorship: Yes
Student Author: Yes
Submission Number: 733
Loading