# Enhancing News Recommendation with Hierarchical LLM Prompting

arXiv: https://arxiv.org/abs/2504.20452 · HTML: https://mlsanity.com/paper/2504.20452/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 16 references that are in the map.
- First posted on arXiv 29 Apr 2025.

## Builds on (most cited first, 11 of 11)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [DKN: Deep Knowledge-Aware Network for News Recommendation](https://mlsanity.com/paper/1801.08284/) (2018)
- [NPA: Neural News Recommendation with Personalized Attention](https://mlsanity.com/paper/1907.05559/) (2019)
- [Empowering News Recommendation with Pre-trained Language Models](https://mlsanity.com/paper/2104.07413/) (2021)
- [Neural News Recommendation with Attentive Multi-View Learning](https://mlsanity.com/paper/1907.05576/) (2019)
- [ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models](https://mlsanity.com/paper/2305.06566/) (2023)
- [Harnessing Large Language Models for Text-Rich Sequential Recommendation](https://mlsanity.com/paper/2403.13325/) (2024)
- [Going Beyond Local: Global Graph-Enhanced Personalized News Recommendations](https://mlsanity.com/paper/2307.06576/) (2023)
- [Generative News Recommendation](https://mlsanity.com/paper/2403.03424/) (2024)
- [DIGAT: Modeling News Recommendation with Dual-Graph Interaction](https://mlsanity.com/paper/2210.05196/) (2022)
- [Benchmarking News Recommendation in the Era of Green AI](https://mlsanity.com/paper/2403.04736/) (2024)

## Abstract (arXiv)

Personalized news recommendation systems often struggle to effectively capture the complexity of user preferences, as they rely heavily on shallow representations, such as article titles and abstracts. To address this problem, we introduce a novel method, namely PNR-LLM, for Large Language Models for Personalized News Recommendation. Specifically, PNR-LLM harnesses the generation capabilities of LLMs to enrich news titles and abstracts, and consequently improves recommendation quality. PNR-LLM contains a novel module, News Enrichment via LLMs, which generates deeper semantic information and relevant entities from articles, transforming shallow contents into richer representations. We further propose an attention mechanism to aggregate enriched semantic- and entity-level data, forming unified user and news embeddings that reveal a more accurate user-news match. Extensive experiments on MIND datasets show that PNR-LLM outperforms state-of-the-art baselines. Moreover, the proposed data enrichment module is model-agnostic, and we empirically show that applying our proposed module to multiple existing models can further improve their performance, verifying the advantage of our design.