Generative News Recommendation
Open Access
- 13 May 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 3444-3453
Abstract
Most existing news recommendation methods tackle this task by conducting semantic matching between candidate news and user representation produced by historical clicked news. However, they overlook the high-level connections among different news articles and also ignore the profound relationship between these news articles and users. And the definition of these methods dictates that they can only deliver news articles as-is. On the contrary, integrating several relevant news articles 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 GNR to implement the generative news recommendation paradigm. First, we compose the dual-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 relation 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 multiple news articles in a coherent narrative. Extensive experiments show that GNR can improve recommendation accuracy and eventually generate more personalized and factually consistent narratives.Keywords
All Related Versions
Funding Information
- Natural Science Foundation of Shandong Province (ZR2023QF159)
- National Natural Science Foundation of China (62272274,T2293773,62372275,62202271,62102234,62072279)
- National Key R&D Program of China (No.2022YFC3303004)
This publication has 21 references indexed in Scilit:
- A comprehensive survey on pretrained foundation models: a history from BERT to ChatGPTInternational Journal of Machine Learning and Cybernetics, 2024
- Leveraging Large Language Models for Sequential Recommendation2023
- Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferences2023
- ConvNTM: Conversational Neural Topic ModelProceedings of the AAAI Conference on Artificial Intelligence, 2023
- Personalized News Recommendation: Methods and ChallengesACM Transactions on Information Systems, 2023
- Empowering News Recommendation with Pre-trained Language Models2021
- MIND: A Large-scale Dataset for News Recommendation2020
- A Survey on Personalized News Recommendation TechnologyIEEE Access, 2019
- DKN2018
- Google news personalization2007